Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Zero to AI
Logo
Zero to AI

Roadmaps

  • Overview
  • Core Systems
  • Advanced Topics
  • End-to-End Flows

Foundations

  • Course Setup
    • AI Model Landscape: March 6, 2026
    • Troubleshooting Guide
  • Python Fundamentals
  • Data Science Foundations
    • How To Become a Data Engineer
    • NumPy Examples - Consolidated & Deduplicated
      • 📊 Content Statistics
      • 💡 Study Tips
      • 📖 Additional Resources
      • 🗺️ Next Steps
      • 01 Basics
        • Data types
        • Comparison Operators
        • Logic Operators
        • if, elif, else Statements
        • for Loops
        • while Loops
        • range()
        • List Comprehension
        • Functions
        • Lambda Expressions
        • map and filter
        • Methods
        • Great Job!
        • Exercises
        • Great job!
        • Load in NumPy
        • The Basics
        • Accessing/Changing Specific Elements, Rows, Columns
        • 3-D Array Example
        • Initializing Different Types of Arrays
        • Be Careful When Copying Arrays
        • Mathematics
        • Linear Algebra
        • Statistics
        • Reorganizing Arrays
        • Miscellaneous
        • NumPy Exercises
        • Great Job!
        • NumPy Operations
        • Great Job!
        • NumPy
        • Numpy Arrays
        • Great Job!
        • NumPy Indexing and Selection
        • Great Job!
      • 02 Intermediate
        • Copy vs. View in NumPy
        • Filtering NumPy Arrays with Boolean Indexing
        • NumPy Universal Functions (ufuncs)
        • Square Root – np.sqrt()
        • Absolute Value – np.absolute()
        • Exponential – np.exp()
        • Min and Max – np.min() / np.max()
        • Sign Function – np.sign()
        • Introduction to NumPy Arrays
        • Array Creation Methods
        • Iterating Over NumPy Arrays
        • Iterating a 1-D Array
        • Iterating 2-D and 3-D Arrays
        • Sorting NumPy Arrays
        • Sorting Numbers
        • Sorting Strings Alphabetically
        • Sorting Booleans
        • Searching NumPy Arrays with np.where()
        • Retrieving Search Results
        • Finding Even and Odd Numbers
        • Reshaping NumPy Arrays
        • 2-D Array Shape
        • Reshaping from 1-D to 2-D
        • Slicing 1-D NumPy Arrays
        • Slicing 2-D NumPy Arrays
      • 03 Exercises
        • 100 numpy exercises
        • 100 numpy exercises
        • Random Sampling
        • Random Sampling – Solutions
        • Set Routines
        • Set Routines – Solutions
        • Sorting, Searching, and Counting
        • Sorting, Searching, and Counting – Solutions
        • Statistics
        • Statistics – Solutions
        • Array Creation Routines
        • Array Creation Routines – Solutions
        • Array Manipulation Routines
        • Array Manipulation Routines – Solutions
        • String Operations
        • Comparison
        • String Information
        • String Operations – Solutions
        • Comparison
        • String Information
        • NumPy-Specific Help Functions
        • NumPy-Specific Help Functions — Solutions
        • Input and Output
        • Input and Output – Solutions
        • Linear Algebra
        • Linear Algebra – Solutions
        • Discrete Fourier Transform
        • Complex Numbers
        • Discrete Fourier Transform
        • Window Functions
        • Complex Numbers
        • Discrete Fourier Transform
        • Window Functions
        • Logic Functions
        • Logic Functions – Solutions
        • Mathematical Functions
        • Mathematical Functions – Solutions
      • 04 Advanced
        • Numpy Tutorials
          • Determining Moore’s Law with real data in NumPy
          • Pairing Jupyter notebooks and MyST-NB
          • Saving and sharing your NumPy arrays
          • Analyzing the impact of the lockdown on air quality in Delhi, India
          • Deep learning on MNIST
          • Deep reinforcement learning with Pong from pixels
          • Masked Arrays
          • Sentiment Analysis on notable speeches of the last decade
          • Plotting Fractals
          • Determining Static Equilibrium in NumPy
          • Learn to write a NumPy tutorial
          • Linear algebra on n-dimensional arrays
          • X-ray image processing
          • NLP from Scratch Tutorial Data
    • Pandas Examples - Consolidated & Organized
      • Pandas Examples Consolidation Summary
      • 📊 What You’ll Learn
      • 💡 Pro Tips for Success
      • 📖 Essential pandas Operations
      • 📈 Progress Tracking
      • 🔗 Additional Resources
      • 📊 Collection Statistics
      • 🎓 Ready to Begin?
      • 01 Basics
        • Differences between Shared Methods
        • Selecting One Column from a DataFrame
        • Select Two or More Columns in DataFrame
        • Add New Column to DataFrame
        • Broadcasting Operations
        • A Review of the .value_counts() Method
        • Drop Rows with Null Values
        • Fill in Null Values with the .fillna() Method
        • The .astype() Method
        • Sort a DataFrame with the .sort_values() Method, Part 1
        • Sort a DataFrame with the .sort_values() Method, Part 2
        • Sort a DataFrame with the .sort_index() Method
        • Rank Values with the .rank() Method
        • Filter a DataFrame Based on a Condition
        • Filter with More than One Condition (AND)
        • Filter with More than One Condition (OR)
        • The .isnull() and .notnull() Methods
        • The .between() Method
        • The .duplicated() Method
        • The .drop_duplicates() Method
        • The .unique() and .nunique() Methods
        • set_index() and reset_index() Methods
        • Retrieve Rows by Index Label with .loc[]
        • Retrieve Row(s) by Index Position with iloc
        • The Catch-All .ix[] Method
        • Second Argument to .loc[], .iloc[], and .ix[] Methods
        • Set New Values for Specific Cell or Row
        • Set Multiple Values in DataFrame
        • Rename Index Labels or Columns in a DataFrame
        • Delete Rows or Columns from a DataFrame
        • Create Random Sample
        • The .nsmallest() and .nlargest() Methods
        • Filtering with the where Method
        • The .query() Method
        • A Review of the .apply() Method on Single Columns
        • The .copy() Method
        • Data Cleaning in Pandas
        • EDA in Pandas
        • Filtering and Ordering
        • Group by and Aggregating
        • Indexing
        • Merge, Join, and Concatenate
        • Pandas Series and DataFrames
        • Reading In Files
        • Pandas Visualization
        • Pandas Numpy Lessons
          • Lesson1
            • Exploratory Analysis
            • Create a Pandas Dataframe
            • Introduction to Pandas
            • Loading data into Pandas
            • Load a CSV from a local file
            • Load JSON from a local file
            • You can read from many formats
            • Writing data from Pandas Dataframes
            • Write to many other destinations
            • Copy/Paste into other formats
          • Lesson2
            • Applying Functions
            • Common Dataframe operations
            • Manipulating text in DataFrames
            • Visualizing data
          • Lesson3
            • Common array operations
            • Introduction to NumPy arrays
            • More array operations
      • 02 Intermediate
        • Apple Health Data – Real-World Data Analysis Project
        • DataFrame Fundamentals – Inspection, Selection, and Cleaning
        • DataFrame Operations – Filtering, Deduplication, and Unique Values
        • DataFrame Operations – Indexing, Renaming, Querying, and Applying Functions
        • Electronic Production in India – Data Analysis and Visualization
        • GroupBy – Split-Apply-Combine for Aggregation
        • Input and Output – Reading and Writing Data
        • Merge, Join, and Concatenate – Combining DataFrames
        • MultiIndex – Hierarchical Indexing, Pivoting, and Reshaping
        • Options and Settings – Controlling Pandas Display Behavior
        • Data Cleaning in Pandas
        • EDA in Pandas
        • Filtering and Ordering
        • Group by and Aggregating
        • Indexing
        • Merge, Join, and Concatenate
        • Pandas Series and DataFrames
        • Reading In Files
        • Pandas Visualization
        • Panels – Three-Dimensional Data Structures (Deprecated)
        • India Electronic Production – Interactive Visualization with Plotly
        • Reading CSV and Working with Series
        • Creating Series in Python
        • Tamil Nadu Population Literacy Analysis
        • Visualization – Plotting Stock Data with Pandas and Matplotlib
        • Working with Date and Time
        • Working with Text Data
        • Geographic Visualization – Flight Path Maps with Plotly
      • 03 Exercises
        • 100 pandas puzzles
        • 100 pandas puzzles
      • 05 Real World Projects
        • Apple Health Data – Real-World Analysis Project
        • Electronic Production in India – Data Analysis and Visualization
        • India Production Data – Advanced Plotly Visualizations
    • Data Science Examples
      • 📖 Study Schedule Examples
      • 💡 Success Tips
      • 🎓 Skill Progression
      • 📊 Track Your Progress
      • 🔗 Essential Resources
      • 🎯 Your Next Steps
      • 💪 Motivation
      • 🚀 Ready to Begin?
      • Data Science for Beginners - A Curriculum
      • Are you a student?
      • Getting Started
        • Microsoft Open Source Code of Conduct
        • Contributing
        • Security
        • Reporting Security Issues
        • Preferred Languages
        • Policy
        • Support
        • Contribute by translating lessons
        • For Educators
        • Using the repo as is
        • Included in this curriculum:
        • Please give us your thoughts!
        • Introduction to Data Science
          • Defining Data Science
            • Assignment: Data Science Scenarios
            • Challenge: Analyzing Text about Data Science
            • Solution
              • Assignment: Data Science Scenarios
              • Challenge: Analyzing Text about Data Science
          • Introduction to Data Ethics
          • Assignment
            • Write A Data Ethics Case Study
            • Instructions
            • Rubric
          • Defining Data
            • Classifying Datasets
          • A Brief Introduction to Statistics and Probability
            • Introduction to Probability and Statistics
            • Assignment
            • Introduction to Probability and Statistics
            • Solution
              • Introduction to Probability and Statistics
              • Assignment
        • Working with Data
          • Working with Data: Relational Databases
            • Displaying airport data
          • Working with Data: Non-Relational Data
            • Soda Profits
          • Working with Data: Python and the Pandas Library
            • Assignment for Data Processing in Python
            • Estimation of COVID-19 Pandemic
            • Analyzing COVID-19 Papers
            • Basic Pandas Examples
            • DataFrame
            • Printing and Plotting
            • R
              • Pandas Usecase in R
              • Series
              • DataFrame
              • Printing and Plotting
          • Working with Data: Data Preparation
            • Assignment: Evaluating Data from a Form
            • Data Preparation
        • Visualizations
          • Visualizing Quantities
            • Lines, Scatters and Bars
            • Let’s learn about birds
            • Solution
              • Let’s learn about birds
          • Visualizing Distributions
            • Apply your skills
            • Bird distributions
            • Solution
              • Bird distributions
          • Visualizing Proportions
            • Try it in Excel
            • 🍄 Mushroom Proportions
            • Solution
              • 🍄 Mushroom Proportions
              • Pie chart
              • Donut chart
              • Waffle chart
          • Visualizing Relationships: All About Honey 🍯
            • Dive into the beehive
            • Visualizing Honey Production 🍯 🐝
            • Solution
              • Visualizing Honey Production 🍯 🐝
          • Making Meaningful Visualizations
            • Build your own custom vis
            • Dangerous Liaisons data visualization project
            • Dangerous Liaisons data visualization project
          • R
            • Visualizing Quantities
              • Lines, Scatters and Bars
            • Visualizing Distributions
              • Apply your skills
            • Visualizing Proportions
            • Visualizing Relationships: All About Honey 🍯
            • Making Meaningful Visualizations
        • The Data Science Lifecycle
          • Introduction to the Data Science Lifecycle
            • Assessing a Dataset
            • NYC Taxi data in Winter and Summer
          • The Data Science Lifecycle: Analyzing
            • NYC Taxi data in Winter and Summer
            • Use the cells below to do your own Exploratory Data Analysis
            • Analyzing Data
          • The Data Science Lifecycle: Communication
          • Introduction
          • Effective Communication
          • Communication Case Study
          • Conclusion
            • Tell a story
        • Data Science in the Cloud
          • Introduction to Data Science in the Cloud
            • Market Research
          • Data Science in the Cloud: The “Low code/No code” way
            • Low code/No code Data Science project on Azure ML
          • Data Science in the Cloud: The “Azure ML SDK” way
            • Data Science project using Azure ML SDK
            • Data Science in the Cloud: The “Azure ML SDK” way
            • Solution
              • Data Science in the Cloud: The “Azure ML SDK” way
        • Data Science in the Wild
          • Data Science in the Real World
            • Explore a Planetary Computer Dataset
        • Docs
        • Quizzes
        • Credits
      • Core Data Science Topics
        • Matplotlib Reference
          • Visualization with Matplotlib
          • Simple Line Plots
          • Simple Scatter Plots
          • Visualizing Errors
          • Density and Contour Plots
          • Histograms, Binnings, and Density
          • Customizing Plot Legends
          • Customizing Colorbars
          • Multiple Subplots
          • Text and Annotation
          • Customizing Ticks
          • Customizing Matplotlib: Configurations and Stylesheets
          • Three-Dimensional Plotting in Matplotlib
          • Geographic Data with Basemap
          • Visualization with Seaborn
          • Further Resources
          • matplotlib-applied
          • matplotlib
        • Numpy Reference
          • Introduction to NumPy
          • Understanding Data Types in Python
          • The Basics of NumPy Arrays
          • Computation on NumPy Arrays: Universal Functions
          • Aggregations: Min, Max, and Everything In Between
          • Computation on Arrays: Broadcasting
          • Comparisons, Masks, and Boolean Logic
          • Fancy Indexing
          • Sorting Arrays
          • Structured Data: NumPy’s Structured Arrays
          • NumPy
        • Pandas Reference
          • Data Manipulation with Pandas
          • Introducing Pandas Objects
          • Data Indexing and Selection
          • Operating on Data in Pandas
          • Handling Missing Data
          • Hierarchical Indexing
          • Combining Datasets: Concat and Append
          • Combining Datasets: Merge and Join
          • Aggregation and Grouping
          • Pivot Tables
          • Vectorized String Operations
          • Working with Time Series
          • High-Performance Pandas: eval() and query()
          • Further Resources
          • Pandas
      • Machine Learning Examples
        • Kaggle Notebooks
          • Kaggle Machine Learning Competition: Predicting Titanic Survivors
        • Scikit Learn Reference
          • Density Estimation: Gaussian Mixture Models
          • Introduction to scikit-learn
          • Machine Learning Models Cheat Sheet
          • The Estimator API
          • The Iris Dataset
          • K-Nearest Neighbors Classifier
          • K-Means Clustering with scikit-learn
          • K-Means on the Iris Dataset
          • The K-Means Algorithm: Expectation Maximization
          • Linear Regression with scikit-learn
          • Linear Regression
          • Principal Component Analysis (PCA) with scikit-learn
          • PCA on the Iris Dataset
          • Dimensionality Reduction: Principal Component Analysis in-depth
          • Random Forests with scikit-learn
          • Decision Trees: The Building Block
          • Creating a Decision Tree
          • Decision Trees and over-fitting
          • Ensembles of Estimators: Random Forests
          • Random Forest Limitations
          • Support Vector Machines (SVM) with scikit-learn
          • Linear SVM Classifier
          • Support Vector Machine with Kernels Classifier
          • Validation and Model Selection
          • Fig Code
            • scikit-learn
      • Deep Learning Examples
        • Tensorflow Keras
          • Deep Dream
            • Deep Dreams (with Caffe)
          • Keras Tutorial
            • Outline (Draft)
            • Yam Peleg, Valerio Maggio
            • Goal of this Tutorial
            • (Tentative) Schedule
            • Requirements
            • How to set up your environment
            • Recreate the Conda Environment
            • Test if everything is up&running
            • Consulting Material
            • Introduction to Deep Learning
            • Artificial Neural Networks (ANN)
            • Building Neural Nets from scratch
            • Addendum
            • Theano
            • Symbolic variables
            • Evaluating expressions
            • Other tensor types
            • Automatic differention
            • Shared Variables
            • Updates
            • About the data
            • Keras
            • “Data Sciencing” this example a little bit more
            • A simple implementation of ANN for MNIST
            • Convolutional Neural Network
            • The Problem Space
            • Convolutional Layer
            • Going Deeper Through the Network
            • CNN in Keras
            • ConvNet HandsOn with Keras
            • Basic data analysis on the dataset
            • Convolution Nets for MNIST
            • A simple CNN
            • Adding more Dense Layers
            • Adding Dropout
            • Adding more Convolution Layers
            • Exercise
            • Batch Normalisation
            • Practical Deep Learning
            • VGG16
            • Fine Tuning of a Pre-Trained Model
            • Hands On:
            • Unsupervised learning
            • Natural Language Processing using Artificial Neural Networks
            • Word Embeddings
            • Convolutional Neural Networks for Sentence Classification
            • Another Example
            • Recurrent Neural networks
            • Sentence Generation using RNN(LSTM)
            • RNN using LSTM
            • Using TFIDF Vectorizer as an input instead of one hot encoder
            • Sentence Generation using LSTM
            • Conclusions
            • Trained image classification models for Keras
          • Tensor Flow Examples
            • Download and Setup
            • Notebooks
              • 1 Intro
                • Basic Operations in TensorFlow
              • 2 Basic Classifiers
                • Linear Regression in TensorFlow
                • Logistic Regression in TensorFlow
                • Nearest Neighbor in TensorFlow
              • 3 Neural Networks
                • AlexNet in TensorFlow
                • Convolutional Neural Network (CNN) in TensorFlow
                • Multilayer Perceptron (MLP) in TensorFlow
                • Recurrent Neural Network (LSTM) in TensorFlow
              • 4 Multi Gpu
                • Basic Multi-GPU Computation in TensorFlow
              • 5 Ui
                • Graph Visualization with TensorBoard
                • Run the command line
                • Open http://localhost:6006/ into your web browser
                • Loss Visualization with TensorBoard
                • Run the command line
                • Open http://localhost:6006/ into your web browser
          • Exercises
            • Deep Learning with TensorFlow
            • Deep Learning with TensorFlow
            • Deep Learning with TensorFlow
            • Deep Learning with TensorFlow
            • Deep Learning with TensorFlow
            • Deep Learning with TensorFlow
          • Theano Tutorial
            • Intro Theano
              • Introduction to Theano
              • Graph definition and Syntax
              • Graph Transformations
              • Advanced Topics
              • Logistic Regression in Theano
            • Rnn Tutorial
              • Introduction
              • Recurrent Neural Networks in Theano
              • Generating sequences
            • Scan Tutorial
              • Introduction to Scan in Theano
            • Theano Mlp
              • Multilayer Perceptron in Theano
      • Reference Notebooks
        • Aws
          • Amazon Web Services (AWS)
        • Spark
          • HDFS
          • Spark
    • Matplotlib
      • Matplotlib interactive examples
      • Plot Types Jupyter
        • 3D
          • 3D Bar Charts
          • 3D Fill Between
          • 3D Line Plots
          • 3D Quiver (Vector Field) Plots
          • 3D Scatter Plots
          • 3D Stem Plots
          • 3D Surface Plots
          • Triangulated Surface Plots
          • Voxel Plots
          • 3D Wireframe Plots
        • Arrays
          • Wind Barb Plots
          • Contour Line Plots
          • Filled Contour Plots
          • Image Display
          • Pseudocolor Mesh Plots
          • 2D Vector Field Plots
          • Streamline Plots
        • Basic
          • Bar Charts
          • Fill Between Curves
          • Line and Marker Plots
          • Scatter Plots
          • Stacked Area Charts
          • Step Function Plots
          • Stem Plots
        • Stats
          • Box and Whisker Plots
          • Empirical Cumulative Distribution Functions
          • Error Bar Plots
          • Event Plots
          • Hexagonal Binning
          • 2D Histograms
          • Histograms
          • Pie Charts
          • Violin Plots
        • Unstructured
          • Contour Lines on Unstructured Grids
          • Filled Contours on Unstructured Grids
          • Pseudocolor Plots on Unstructured Grids
          • Triangulation Visualization
    • Scikit-Learn Examples
      • Applications
        • Plot Cyclical Feature Engineering
        • Plot Digits Denoising
        • Plot Face Recognition
        • Plot Model Complexity Influence
        • Plot Out Of Core Classification
        • Plot Outlier Detection Wine
        • Plot Prediction Latency
        • Plot Species Distribution Modeling
        • Plot Stock Market
        • Plot Time Series Lagged Features
        • Plot Tomography L1 Reconstruction
        • Plot Topics Extraction With Nmf Lda
        • Wikipedia Principal Eigenvector
      • Bicluster
        • Plot Bicluster Newsgroups
        • Plot Spectral Biclustering
        • Plot Spectral Coclustering
      • Calibration
        • Plot Calibration
        • Plot Calibration Curve
        • Plot Calibration Multiclass
        • Plot Compare Calibration
      • Classification
        • Plot Classification Probability
        • Plot Classifier Comparison
        • Plot Digits Classification
        • Plot Lda
        • Plot Lda Qda
      • Cluster
        • Plot Adjusted For Chance Measures
        • Plot Affinity Propagation
        • Plot Agglomerative Clustering Metrics
        • Plot Hierarchical Clustering Dendrogram
        • Plot Birch Vs Minibatchkmeans
        • Plot Bisect Kmeans
        • Plot Cluster Comparison
        • Plot Coin Segmentation
        • Plot Coin Ward Segmentation
        • Plot Dbscan
        • Plot Dict Face Patches
        • Plot Digits Agglomeration
        • Plot Digits Linkage
        • Plot Face Compress
        • Plot Feature Agglomeration Vs Univariate Selection
        • Demo of HDBSCAN Clustering Algorithm
        • Plot Inductive Clustering
        • Plot Kmeans Assumptions
        • Plot Kmeans Digits
        • Plot Kmeans Plusplus
        • Plot Kmeans Silhouette Analysis
        • Plot Kmeans Stability Low Dim Dense
        • Plot Linkage Comparison
        • Plot Mean Shift
        • Plot Mini Batch Kmeans
        • Plot Optics
        • Plot Segmentation Toy
        • Plot Ward Structured Vs Unstructured
      • Compose
        • Plot Column Transformer
        • Plot Column Transformer Mixed Types
        • Plot Compare Reduction
        • Plot Digits Pipe
        • Plot Feature Union
        • Plot Transformed Target
      • Covariance
        • Plot Covariance Estimation
        • Plot Lw Vs Oas
        • Robust Covariance Estimation and Mahalanobis Distances
        • Robust vs Empirical Covariance Estimate
        • Plot Sparse Cov
      • Cross Decomposition
        • Plot Compare Cross Decomposition
        • Plot Pcr Vs Pls
      • Datasets
        • Plot Random Multilabel Dataset
      • Decomposition
        • Plot Faces Decomposition
        • Plot Ica Blind Source Separation
        • Plot Ica Vs Pca
        • Plot Image Denoising
        • Plot Incremental Pca
        • Plot Kernel Pca
        • Plot Pca Iris
        • Plot Pca Vs Fa Model Selection
        • Plot Pca Vs Lda
        • Plot Sparse Coding
        • Plot Varimax Fa
      • Developing Estimators
        • Sklearn Is Fitted
      • Ensemble
        • Plot Adaboost Multiclass
        • Plot Adaboost Regression
        • Plot Adaboost Twoclass
        • Plot Bias Variance
        • Plot Ensemble Oob
        • Plot Feature Transformation
        • Plot Forest Hist Grad Boosting Comparison
        • Plot Forest Importances
        • Plot Forest Iris
        • Plot Gradient Boosting Categorical
        • Plot Gradient Boosting Early Stopping
        • Plot Gradient Boosting Oob
        • Plot Gradient Boosting Quantile
        • Plot Gradient Boosting Regression
        • Plot Gradient Boosting Regularization
        • Plot Hgbt Regression
        • Plot Isolation Forest
        • Plot Monotonic Constraints
        • Plot Random Forest Embedding
        • Plot Random Forest Regression Multioutput
        • Plot Stack Predictors
        • Plot Voting Decision Regions
        • Plot Voting Regressor
      • Feature Selection
        • Plot F Test Vs Mi
        • Plot Feature Selection
        • Plot Feature Selection Pipeline
        • Plot Rfe Digits
        • Plot Rfe With Cross Validation
        • Plot Select From Model Diabetes
      • Frozen
        • Plot Frozen Examples
      • Gaussian Process
        • Plot Compare Gpr Krr
        • Plot Gpc
        • Plot Gpc Iris
        • Plot Gpc Isoprobability
        • Plot Gpc Xor
        • Plot Gpr Co2
        • Plot Gpr Noisy
        • Plot Gpr Noisy Targets
        • Plot Gpr On Structured Data
        • Plot Gpr Prior Posterior
      • Impute
        • Plot Iterative Imputer Variants Comparison
        • Plot Missing Values
      • Inspection
        • Plot Causal Interpretation
        • Plot Linear Model Coefficient Interpretation
        • Plot Partial Dependence
        • Plot Permutation Importance
        • Plot Permutation Importance Multicollinear
      • Kernel Approximation
        • Plot Scalable Poly Kernels
      • Linear Model
        • Plot Ard
        • Plot Bayesian Ridge Curvefit
        • Plot Elastic Net Precomputed Gram Matrix With Weighted Samples
        • Plot Huber Vs Ridge
        • Plot Lasso And Elasticnet
        • Plot Lasso Dense Vs Sparse Data
        • Plot Lasso Lars Ic
        • Plot Lasso Lasso Lars Elasticnet Path
        • Plot Lasso Model Selection
        • Plot Logistic L1 L2 Sparsity
        • Plot Logistic Multinomial
        • Plot Logistic Path
        • Plot Multi Task Lasso Support
        • Plot Nnls
        • Plot Ols Ridge
        • Plot Omp
        • Poisson Regression and Non-Normal Loss
        • Plot Polynomial Interpolation
        • Plot Quantile Regression
        • Plot Ransac
        • Plot Ridge Coeffs
        • Plot Ridge Path
        • Plot Robust Fit
        • Plot Sgd Early Stopping
        • Plot Sgd Iris
        • Plot Sgd Loss Functions
        • Plot Sgd Penalties
        • Plot Sgd Separating Hyperplane
        • Plot Sgd Weighted Samples
        • Plot Sgdocsvm Vs Ocsvm
        • Plot Sparse Logistic Regression 20Newsgroups
        • Plot Sparse Logistic Regression Mnist
        • Plot Theilsen
        • Tweedie Regression on Insurance Claims
      • Manifold
        • Plot Compare Methods
        • Plot Lle Digits
        • Plot Manifold Sphere
        • Plot Mds
        • Plot Swissroll
        • Plot T Sne Perplexity
      • Miscellaneous
        • Plot Anomaly Comparison
        • Plot Display Object Visualization
        • Plot Estimator Representation
        • Plot Isotonic Regression
        • The Johnson-Lindenstrauss Bound for Random Projections
        • Plot Kernel Approximation
        • Plot Kernel Ridge Regression
        • Plot Metadata Routing
        • Plot Multilabel
        • Plot Multioutput Face Completion
        • Plot Outlier Detection Bench
        • Plot Partial Dependence Visualization Api
        • Plot Pipeline Display
        • Plot Roc Curve Visualization Api
        • Plot Set Output
      • Mixture
        • Plot Concentration Prior
        • Plot Gmm
        • Plot Gmm Covariances
        • Plot Gmm Init
        • Plot Gmm Pdf
        • Plot Gmm Selection
        • Plot Gmm Sin
      • Model Selection
        • Plot Confusion Matrix
        • Plot Cost Sensitive Learning
        • Plot Cv Indices
        • Plot Cv Predict
        • Plot Det
        • Plot Grid Search Digits
        • Plot Grid Search Refit Callable
        • Plot Grid Search Stats
        • Plot Grid Search Text Feature Extraction
        • Plot Learning Curve
        • Plot Likelihood Ratios
        • Plot Multi Metric Evaluation
        • Plot Nested Cross Validation Iris
        • Plot Permutation Tests For Classification
        • Plot Precision Recall
        • Plot Randomized Search
        • Plot Roc
        • Plot Roc Crossval
        • Plot Successive Halving Heatmap
        • Plot Successive Halving Iterations
        • Plot Train Error Vs Test Error
        • Plot Tuned Decision Threshold
        • Plot Underfitting Overfitting
      • Multiclass
        • Plot Multiclass Overview
      • Multioutput
        • Plot Classifier Chain Yeast
      • Neighbors
        • Approximate Nearest Neighbors
        • Plot Caching Nearest Neighbors
        • Plot Classification
        • Plot Digits Kde Sampling
        • Plot Kde 1D
        • Plot Lof Novelty Detection
        • Plot Lof Outlier Detection
        • Plot Nca Classification
        • Plot Nca Dim Reduction
        • Plot Nca Illustration
        • Plot Nearest Centroid
        • Plot Regression
        • Plot Species Kde
      • Neural Networks
        • Plot Mlp Alpha
        • Plot Mlp Training Curves
        • Plot Mnist Filters
        • Plot Rbm Logistic Classification
      • Preprocessing
        • Plot All Scaling
        • Plot Discretization
        • Plot Discretization Classification
        • Plot Discretization Strategies
        • Plot Map Data To Normal
        • Plot Scaling Importance
        • Plot Target Encoder
        • Plot Target Encoder Cross Val
      • Release Highlights
        • Plot Release Highlights 0 22 0
        • Release Highlights for scikit-learn 0.23
        • Release Highlights for scikit-learn 0.24
        • Release Highlights for scikit-learn 1.0
        • Release Highlights for scikit-learn 1.1
        • Release Highlights for scikit-learn 1.2
        • Release Highlights for scikit-learn 1.3
        • Release Highlights for scikit-learn 1.4
        • Release Highlights for scikit-learn 1.5
        • Release Highlights for scikit-learn 1.6
        • Release Highlights for scikit-learn 1.7
        • Release Highlights for scikit-learn 1.8
      • Semi Supervised
        • Plot Label Propagation Digits
        • Plot Label Propagation Digits Active Learning
        • Plot Label Propagation Structure
        • Plot Self Training Varying Threshold
        • Plot Semi Supervised Newsgroups
        • Plot Semi Supervised Versus Svm Iris
      • Svm
        • Plot Custom Kernel
        • Plot Iris Svc
        • Plot Linearsvc Support Vectors
        • Plot Oneclass
        • Plot Rbf Parameters
        • Plot Separating Hyperplane
        • Plot Separating Hyperplane Unbalanced
        • Plot Svm Anova
        • Plot Svm Kernels
        • Plot Svm Margin
        • Plot Svm Regression
        • Scaling the Regularization Parameter for SVCs
        • Plot Svm Tie Breaking
        • Plot Weighted Samples
      • Text
        • Plot Document Classification 20Newsgroups
        • Plot Document Clustering
        • Plot Hashing Vs Dict Vectorizer
      • Tree
        • Plot Cost Complexity Pruning
        • Plot Iris Dtc
        • Plot Tree Regression
        • Plot Unveil Tree Structure
  • Mathematics for ML
    • 3Blue1Brown Visual Mathematics
      • Calculus (3Blue1Brown)
        • Chapter 1: The Essence of Calculus
        • Chapter 2: The Paradox of the Derivative
        • Chapter 3: Derivative Formulas through Geometry
        • Chapter 4: Visualizing the Chain Rule and Product Rule
        • Chapter 5: Derivatives of Exponential
        • Chapter 6: Implicit Differentiation
        • Chapter 7: Limits and L’Hopital’s Rule
        • Chapter 8: Integration and the Fundamental Theorem
        • Chapter 9: What Does Area Have to Do with Slope?
        • Chapter 10: Higher Order Derivatives
        • Chapter 11: Taylor Series
        • Chapter 12: What Makes \(e^x\) So Special?
      • Chapter 1: Differential Equations - Introduction
      • Chapter 2: The Heat Equation
      • Chapter 3: Solving the Heat Equation
      • Chapter 4: Fourier Series and Complex Exponential
      • Chapter 5: Laplace Transforms
      • Chapter 6: Understanding the Laplace Transform
      • Chapter 7: Resonance and Forced Oscillations
      • Chapter 8: Matrix Exponents
      • Chapter 1: Abstract Vector Spaces
      • Chapter 2: Linear combinations, span, and basis vectors
      • Chapter 3: Linear transformations and matrices
      • Chapter 4: Matrix multiplication as composition
      • Chapter 5: Three-dimensional linear transformations
      • Chapter 6: The determinant
      • Chapter 7: Inverse matrices, column space and null space
      • Chapter 8: Nonsquare matrices as transformations between dimensions
      • Chapter 9: Dot products and duality
      • Chapter 10: Three-Dimensional Linear Transformations
      • Chapter 12: Cramer’s rule, explained geometrically
      • Chapter 13: Change of basis
      • Chapter 16: Abstract Vector Spaces
      • Chapter 1: But What is a Neural Network?
      • Chapter 2: Gradient Descent
      • Chapter 3: What is Backpropagation?
      • Chapter 4: Backpropagation Calculus
      • Chapter 5: GPT and Large Language Models
      • Chapter 6: Attention in Transformers
      • Chapter 7: Attention Mechanism Deep Dive
      • Chapter 8: How GPT Stores Facts
      • Chapter 9: Diffusion Models
    • Advanced Mathematics for Machine Learning
      • 1. The Learning Problem
      • 2. Generalization: The Core Challenge
      • Advanced Statistical Learning Theory
      • 3. The Bias-Variance Tradeoff
      • 4. Sample Complexity
      • 5. PAC Learning Framework
      • 6. Summary
      • 7. Exercises
      • References
      • 1. The Sampling Problem
      • 2. Markov Chain Basics
      • 3. Metropolis-Hastings Algorithm
      • 4. Gibbs Sampling
      • 5. Convergence and Diagnostics
      • 6. Summary
      • 1. Rademacher Complexity Definition
      • 2. Generalization Bound via Rademacher Complexity
      • 3. Rademacher Complexity for Different Hypothesis Classes
      • 4. Connection to Generalization
      • 5. Comparison: Rademacher Complexity vs VC Dimension
      • 6. Advanced: Gaussian Complexity
      • Summary
      • 1. PAC-Bayes Framework
      • 2. Proof Sketch
      • 3. Application: Gaussian Posterior over Weights
      • 4. Training with PAC-Bayes Bound
      • 5. Advantages of PAC-Bayes
      • Summary
      • 1. Motivation: Neural Networks as Kernel Methods
      • 2. Linearized Training Dynamics
      • 3. Computing NTK for Simple Networks
      • 4. Empirical NTK via Jacobian
      • 5. Training Dynamics: Kernel Gradient Descent
      • 6. NTK Evolution During Training
      • 7. Theoretical Implications
      • Summary
      • 1. Motivation: The Intractability Problem
      • 2. Evidence Lower Bound (ELBO)
      • 3. Mean-Field Approximation
      • 4. Example: Bayesian Gaussian Mixture (Simple Case)
      • 5. Black Box Variational Inference (BBVI)
      • Summary
      • 1. Motivation: Infinite Flexibility
      • 2. Dirichlet Distribution Review
      • 3. Dirichlet Process (DP)
      • 4. Chinese Restaurant Process (CRP)
      • 5. DP Mixture Model for Clustering
      • Summary
      • 1. The EM Framework
      • 2. Mathematical Derivation
      • 3. Convergence Proof
      • 4. Gaussian Mixture Model (GMM)
      • 5. EM for GMM
      • 6. Visualizing the E and M Steps
      • 7. Summary
      • 1. Function Properties
      • 2. Gradient Descent Algorithm
      • 3. Convergence for L-Smooth Functions
      • 4. Strong Convexity: Linear Convergence
      • 5. Summary of Convergence Rates
      • Summary
      • 1. State Space Model
      • 2. Kalman Filter Algorithm
      • 3. Kalman Smoother (RTS)
      • Summary
      • 1. Motivation
      • 2. Sklar’s Theorem
      • 3. Common Copula Families
      • 4. Application: Constructing Joint Distributions
      • Summary
      • 1. Motivation: Diversity
      • 2. DPP Definition
      • 3. L-ensemble DPP
      • 4. Sampling Algorithm
      • 5. Application: Diverse Subset Selection
      • Summary
      • 1. The Johnson-Lindenstrauss Lemma
      • 2. Random Projection
      • 3. Implementation
      • 4. Sparse Random Projections
      • 5. Application: Nearest Neighbors
      • Summary
      • 1. Primal Problem
      • 2. Dual Problem
      • 3. KKT Conditions
      • 4. Application: SVM Dual
      • Summary
      • 1. Problem: Solve \(Ax = b\)
      • 2. Conjugate Directions
      • 3. Convergence Analysis
      • 4. Preconditioned CG
      • Summary
      • 1. Matrix Bernstein Inequality
      • 2. Matrix Chernoff Bound
      • 3. Random Matrix Theory
      • 4. Marchenko-Pastur Law
      • 5. Application: Compressed Sensing
      • Summary
    • Stanford CS229 Machine Learning
      • CS229: Machine Learning Course (Stanford University)
        • Lecture 1: Introduction & Linear Regression
        • Lecture 2: Linear Regression and Gradient Descent
        • Lecture 3: Locally Weighted Regression (LWR)
        • Lecture 3 & 4: Logistic Regression & Classification
        • Lecture 5 & 6: Generative Learning Algorithms
        • Lecture 6-7: Support Vector Machines
        • Lecture 8: Bias, Variance, and Regularization
        • Lecture 9: Learning Theory
        • Lecture 10: Decision Trees and Ensemble Methods
        • Lecture 11: Introduction to Neural Networks
        • Lecture 12: Backpropagation & Deep Learning
        • Lecture 13: Advice for Applying Machine Learning
        • Lecture 14: Expectation Maximization & Clustering
        • Lectures 15-17: EM, Factor Analysis, PCA & ICA
        • Lectures 18-20: Reinforcement Learning & MDPs
        • CS229 Practice Problems
        • Anomaly Detection
        • Recommender Systems
    • Practice Labs: Deep Learning Interviews (Kashani)
      • Lab 01: Logistic Regression from Scratch
      • Lab 02: Information Theory & Entropy
      • Lab 03: Calculus, Gradients & Backpropagation
      • Lab 04: Probability & Bayesian Deep Learning
      • Lab 05: Neural Network Ensembles
      • Lab 06: CNN Feature Extraction & Deep Learning Fundamentals
    • Foundational Mathematics
      • Setup: Install Required Packages
      • 1. NumPy: Numerical Python
      • 2. Matplotlib: Visualization Basics
      • 3. Seaborn: Beautiful Statistical Plots
      • 4. SciPy: Scientific Computing
      • 5. scikit-learn: Machine Learning Library
      • Quick Reference Cheat Sheet
      • Practice Exercise
      • Bonus: Next Steps Examples
      • 🎓 Your Learning Journey
      • Linear Algebra Fundamentals
      • Calculus & Derivatives
      • Probability & Statistics
      • Gradient Descent
      • Information Theory
      • Statistical Inference
      • Neural Network Mathematics
      • Advanced Linear Algebra
      • The Architecture of Mathematics: Analytical vs Numerical Approaches
      • AI Foundations: Symbolic vs Non-Symbolic AI & Control Theory
      • Markov Models & Hidden Markov Models (HMMs)
      • Optimization from Scratch: Gradient Descent & Adam
    • Introduction to Statistical Learning with Python (ISLP)
      • Statistics & Probability for AI/ML
      • Chapter 1: Introduction to Statistical Learning
      • Chapter 2: Statistical Learning
      • Chapter 3: Linear Regression
      • Chapter 4: Classification
      • Chapter 5: Resampling Methods
      • Chapter 6: Linear Model Selection and Regularization
      • Chapter 7: Moving Beyond Linearity
      • Chapter 8: Tree-Based Methods
      • Chapter 9: Support Vector Machines
      • Chapter 10: Deep Learning
      • Chapter 11: Survival Analysis and Censored Data
      • Chapter 12: Unsupervised Learning
      • Chapter 13: Multiple Testing
      • ISLP Practice Exercises
      • Part 1: Probability Fundamentals
      • Part 2: Descriptive Statistics
      • Part 3: Probability Distributions
      • Part 4: Statistical Inference
      • Part 5: Hypothesis Testing
      • Part 6: Correlation & Causation
      • Part 7: ML Applications
      • 🎯 Summary & Key Takeaways
      • 📚 Additional Resources
    • ML Problem Solving
    • Machine Learning: A Probabilistic Perspective
      • 1. Basic Probability Rules
      • 2. Bayes’ Rule
      • 3. Common Probability Distributions
      • 4. Monte Carlo Sampling
      • 5. Information Theory Basics
      • Summary
      • Exercises
      • 1. Naive Bayes Classifier
      • 2. Gaussian Discriminant Analysis (GDA)
      • 3. Generative vs Discriminative Models
      • 4. Spam Detection with Naive Bayes
      • 5. Effect of the Naive Assumption
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Multivariate Gaussian Distribution
      • 2. Maximum Likelihood Estimation
      • 3. Gaussian Mixture Models (GMM)
      • 4. Expectation-Maximization (EM) Algorithm
      • 5. Missing Data Imputation with EM
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Bayesian Inference Fundamentals
      • 2. Conjugate Priors
      • 3. Posterior Predictive Distribution
      • 4. Bayesian Decision Theory
      • 5. Empirical Bayes
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Linear Regression
      • 2. Ridge Regression (L2 Regularization)
      • 3. Bayesian Linear Regression
      • 4. Logistic Regression for Binary Classification
      • 5. Multinomial Logistic Regression (Softmax)
      • 6. Model Selection and Regularization Comparison
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Lasso Regression (L1 Regularization)
      • 2. Regularization Path: Ridge vs Lasso
      • 3. Elastic Net: Combining L1 and L2
      • 4. Feature Selection with Lasso
      • 5. Sparse Logistic Regression
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Kernel Functions and the Kernel Trick
      • 2. Kernel Ridge Regression
      • 3. Support Vector Machines (SVM)
      • 4. Gaussian Processes for Regression
      • 5. GP Hyperparameter Optimization
      • Summary
      • Key Takeaways
      • When to Use
      • Exercises
      • 1. Bayesian Network Basics
      • 2. Conditional Independence and d-Separation
      • 3. Naive Bayes Classifier
      • 4. Markov Chains
      • Summary
      • Key Takeaways
      • Exercises
      • 1. Hidden Markov Model Definition
      • 2. Forward Algorithm (Filtering)
      • 3. Backward Algorithm
      • 4. Viterbi Algorithm (Decoding)
      • 5. Baum-Welch Algorithm (Learning)
      • 6. Application: Part-of-Speech Tagging
      • Summary
      • Key Takeaways
      • Computational Complexity
      • Limitations
      • Extensions
      • Exercises
      • 1. Monte Carlo Basics
      • 2. Metropolis-Hastings Algorithm
      • MCMC Theory: Advanced Mathematical Foundations
      • 3. Gibbs Sampling
      • 4. Convergence Diagnostics
      • 5. Bayesian Linear Regression with MCMC
      • Summary
      • Key Takeaways
      • Comparison
      • Modern MCMC
      • Exercises
      • 1. Gaussian Mixture Models (GMM)
      • 2. K-Means as Hard EM
      • 3. EM Algorithm Theory
      • 4. EM for GMM
      • 5. Model Selection (BIC, AIC)
      • 6. Mixture of Bernoullis
      • Summary
      • Key Takeaways
      • Extensions
      • Exercises
      • 1. Principal Component Analysis (PCA)
      • 2. Probabilistic PCA
      • 3. Factor Analysis (FA)
      • 4. Independent Component Analysis (ICA)
      • Summary
      • Comparison Table
      • Key Insights
      • Practical Tips
      • Exercises
      • 1. K-Means Clustering (Detailed)
      • 2. Hierarchical Clustering
      • 3. Spectral Clustering
      • 4. DBSCAN (Density-Based)
      • 5. Affinity Propagation
      • 6. Cluster Evaluation Metrics
      • Summary
      • Algorithm Comparison
      • Choosing an Algorithm
      • Practical Tips
      • Exercises
    • Mathematics for Machine Learning (MML)
      • Course
        • 2.1 Systems of Linear Equations
        • 2.2 Matrices
        • 2.3 Solving Systems of Linear Equations
        • 2.4 Vector Spaces
        • 2.5 Linear Independence
        • 2.6 Basis and Rank
        • 2.7 Linear Mappings
        • 2.8 Affine Spaces
        • Summary
        • 3.1 Norms
        • 3.2 Inner Products
        • 3.3 Lengths and Distances
        • 3.4 Angles and Orthogonality
        • 3.5 Orthonormal Basis
        • 3.8 Orthogonal Projections
        • 3.9 Rotations
        • Summary
        • 4.1 Determinant and Trace
        • 4.2 Eigenvalues and Eigenvectors
        • 4.3 Cholesky Decomposition
        • 4.4 Eigendecomposition and Diagonalization
        • 4.5 Singular Value Decomposition (SVD)
        • 4.6 Matrix Approximation
        • Summary
        • 5.1 Differentiation of Univariate Functions
        • 5.2 Partial Differentiation and Gradients
        • 5.3 Gradients of Vector-Valued Functions
        • 5.6 Backpropagation and Automatic Differentiation
        • 5.7 Higher-Order Derivatives
        • 5.8 Linearization and Multivariate Taylor Series
        • Summary
        • 6.1 Probability Space
        • 6.2 Discrete and Continuous Probabilities
        • 6.3 Sum Rule, Product Rule, and Bayes’ Theorem
        • 6.4 Summary Statistics and Independence
        • 6.5 Gaussian Distribution
        • Summary
        • 7.1 Gradient Descent
        • Advanced Optimization Theory for Deep Learning
        • 7.2 Constrained Optimization and Lagrange Multipliers
        • 7.3 Convex Optimization
        • Summary
        • 9.1 Problem Formulation
        • 9.2 Maximum Likelihood Estimation (MLE)
        • 9.3 Regularization: Ridge and Lasso
        • 9.4 Bayesian Linear Regression
        • 9.5 Model Selection and Evaluation
        • Summary
        • 10.1 Problem Setting
        • 10.2 Maximum Variance Perspective
        • 10.3 Projection Perspective
        • 10.4 PCA Algorithm
        • 10.5 PCA on Real Data: Handwritten Digits
        • 10.6 PCA for Data Preprocessing
        • Summary
        • 11.1 Gaussian Mixture Model
        • 11.2 Expectation-Maximization (EM) Algorithm
        • 11.3 Soft vs Hard Clustering
        • 11.4 Model Selection: Choosing K
        • 11.5 GMM Applications and Limitations
        • Summary
        • 12.1 Separating Hyperplanes
        • 12.2 Maximum Margin
        • 12.3 Primal Optimization Problem
        • 12.4 Dual Problem and Lagrange Multipliers
        • 12.5 Kernel Trick
        • 12.6 Soft Margin SVM
        • Summary
      • Exercises
        • Chapter 2: Linear Algebra
        • Chapter 3: Analytic Geometry
        • Chapter 4: Matrix Decompositions
        • Chapter 5: Vector Calculus
        • Chapter 6: Probability and Distributions
        • Chapter 7: Continuous Optimization
        • 🎯 Bonus Challenge: Integration Exercise 🔴🔴
        • Chapter 9: Linear Regression
        • Chapter 10: PCA (Principal Component Analysis)
        • Chapter 11: Gaussian Mixture Models
        • Chapter 12: Support Vector Machines
        • 🎯 Bonus Challenge: Complete ML Pipeline 🔴🔴
        • Chapter 2: Linear Algebra Solutions
        • Chapter 3: Analytic Geometry Solutions
        • Chapter 4: Matrix Decompositions Solutions
        • Chapter 9: Linear Regression Solutions
        • Chapter 10: PCA Solutions
      • Practice Labs: Math for ML (MML Book)
        • Lab 01: Linear Algebra
        • Lab 02 – Analytic Geometry
        • Lab 03: Matrix Decompositions
        • Lab 04: Vector Calculus
        • Lab 05: Probability and Distributions
        • Lab 6: Continuous Optimization
        • Lab 07: Linear Regression
        • Lab 08: Dimensionality Reduction with Principal Component Analysis
        • Lab 09: Density Estimation with Gaussian Mixture Models
        • Lab 10: Classification with Support Vector Machines
    • Practice Labs: SLP (Jurafsky/Martin)
      • Lab 01: Words, Tokens & Text Processing
      • Lab 02: N-gram Language Models
      • Lab 03: Word Embeddings
      • Lab 04: Neural Networks from Scratch
      • Lab 05: Transformers & Attention
      • Lab 06: Large Language Models

Core AI

  • Tokenization
    • Production Tokenization Guide
    • Tokenization Comparison Guide
    • Integration Guide: Using Tokenizers with Popular Frameworks
    • Understanding Tokens
    • HuggingFace Tokenizers - Complete Learning Module
    • HuggingFace Tokenizers Library - Complete Learning Guide
    • Understanding Tokens: The Foundation of Language Models
    • Tokenization — Start Here
    • 01 Tokenizers Quickstart
    • HuggingFace Tokenizers - Quick Start Examples
    • 02 Tokenizers Training
    • HuggingFace Tokenizers - Training Examples
    • 03 Advanced Training Methods
    • Advanced Training Methods for Tokenizers
    • Setup
    • Part 1: Normalization
    • Part 2: Pre-tokenization
    • Part 3: Post-processing
    • Part 4: Decoders
    • Part 5: Complete Pipeline Examples
    • Summary
    • Sentencepiece Example
    • Tiktoken Example
    • Basic Tokenization Example
    • Token Exercises
    • Token Exercises - Interactive Practice
    • Token Exploration
    • Token Exploration - Advanced Examples
  • Embeddings
    • Quick Start Guide - Embeddings
    • Embedding Models Comparison Guide
    • Embeddings — Start Here
    • Embeddings Intro
    • Embeddings Introduction
    • Huggingface Embeddings
    • Openai Embeddings
    • Paraphrase Mining With Sentence Transformers
    • Semantic Search With Sentence Transformers
    • Semantic Similarity
    • Semantic Similarity Explorer
    • Semantic Textual Similarity (STS)
    • Sentence Transformers Quickstart
    • Sparse Encoders: SPLADE and Learned Sparse Representations
    • Vector Database Demo
    • Vector Database Demo
  • Neural Networks
    • Assignment: Build a Neural Network from Scratch
    • Attention Mechanism: The Breakthrough Innovation
    • Challenges: Neural Networks
    • Neural Networks: From Basics to Transformers
    • Transformer Architecture: Complete Guide
    • Verify Installation
    • 🎯 What You’ll Build
    • 🧪 Quick Neural Network Demo
    • 📖 Reading Material
    • 🎓 Prerequisites Review
    • 🚦 Next Steps
    • 📊 Progress Tracker
    • 🎯 Learning Goals
    • 🔗 Helpful Resources
    • 🚀 Let’s Begin!
    • What is a Neuron?
    • 2. Activation Functions
    • 3. Building a Neural Network Layer
    • 4. Building a Complete Neural Network
    • 5. Training a Neural Network
    • 6. Visualizing Decision Boundaries
    • 7. Experimenting with Architecture
    • Summary
    • The Problem
    • 2. The Chain Rule - Foundation of Backpropagation
    • 3. Backpropagation in a Simple Network
    • 4. Training with Backpropagation
    • 5. Multi-Layer Network with Matrix Operations
    • 6. Vanishing and Exploding Gradients
    • Summary
    • Creating Tensors
    • Tensor Operations
    • 2. Automatic Differentiation (Autograd)
    • 3. Building Neural Networks with nn.Module
    • 4. Training a Neural Network – The Complete Loop
    • 5. Modern Optimizers
    • 6. Real Dataset – MNIST Digit Classification
    • 7. Saving and Loading Models
    • Summary
    • Before Attention: The Bottleneck Problem
    • 2. Scaled Dot-Product Attention
    • Attention Mechanism: Mathematical Foundations
    • 3. Self-Attention Example – Understanding Context
    • 4. Multi-Head Attention
    • 5. Masked Attention - For Autoregressive Models
    • 6. Cross-Attention - Connecting Two Sequences
    • 7. Practical Application – Sequence Classification
    • Summary
    • Why Transformers Changed Everything
    • 2. Positional Encoding
    • 3. Feedforward Network
    • 4. Transformer Encoder Layer
    • 5. Complete Transformer Encoder
    • 6. Simple Classification with Transformer
    • 7. Using Pre-trained Transformers
    • 8. Fine-tuning Example
    • 9. Transformer Architecture Diagram
    • Summary
    • 🎓 Congratulations!

Applied AI

  • Vector Databases
    • 📖 Learning Path
    • 🎯 Prerequisites
    • 🗄️ Database Comparison
    • 💡 Common Use Cases
    • 🔗 Additional Resources
    • 🚦 Ready to Start?
    • 🗺️ Your Complete Learning Journey
    • 1. Understanding Vectors and Embeddings
    • 2. Similarity Metrics
    • 3. Why Vector Databases?
    • 4. Simple Vector Database Implementation
    • 5. Using Our Simple Vector Database
    • 6. Update and Delete Operations
    • 7. Real-World Example with Sentence Embeddings
    • 8. Performance Comparison: Different Metrics
    • Key Takeaways
    • Next Steps
    • Chroma – Local Vector Database
    • Qdrant – Production Vector Database
    • Weaviate – Enterprise Vector Database
    • Milvus – Large-Scale Vector Database
    • 1. Connection Setup
    • 2. Enable pgvector Extension
    • 3. Create Tables for Embeddings
    • 4. Generate and Store Embeddings
    • 5. Semantic Search
    • 6. Filtered Semantic Search
    • 7. Hybrid Search (Vector + Full-Text)
    • 8. Product Search Example
    • 9. Performance Optimization
    • 10. Monitoring and Statistics
    • 11. Best Practices
    • 12. Integration with AWS Services
    • 13. Cleanup
    • Summary
  • RAG
    • RAG Evaluation Playbook
    • RAG Technique Selection Guide
    • Assignment: Build a Production-Ready RAG System
    • Challenges: RAG Systems
    • RAG: Retrieval-Augmented Generation - START HERE
    • Basic RAG from Scratch
    • Document Processing and Chunking
    • LangChain RAG
    • LlamaIndex RAG
    • Advanced Retrieval
    • Conversational RAG
    • RAG Evaluation
    • HyDE + Reranking for RAG
    • Advanced RAG Techniques (2025-2026 State of the Art)
    • GraphRAG and Visual RAG (Microsoft GraphRAG + ColPali)
    • Section A: Microsoft GraphRAG
    • Section B: ColPali Visual Document RAG
    • Corrective RAG (CRAG-Style)
    • Parent-Child Retrieval for RAG
    • RAPTOR-Style Hierarchical Retrieval
  • MLOps
    • MLOps: Machine Learning in Production
    • Experiment Tracking with MLflow
    • Building ML APIs with FastAPI
    • Model Deployment Strategies
    • Containerizing ML Applications with Docker
    • Monitoring ML Models in Production
    • CI/CD for Machine Learning
    • Cloud Deployment for ML Models
    • LLM Infrastructure for Production (2025-2026 Essential Stack)
    • LLM Production Optimization
  • Specializations
    • AI Specializations — Start Here
    • AI Agents Specialization
      • AI Agents Series - Completion Summary
      • AI Agents Specialization — Start Here
      • Function Calling & Tool Use
      • ReAct: Reasoning + Acting Agents
      • LangGraph: Stateful Agent Workflows
      • Multi-Agent Systems
      • Memory & State Management for Agents
      • Deploying Agents to Production
    • Computer Vision Specialization
      • Computer Vision Specialization — Start Here
      • Image Classification with Deep Learning
      • Object Detection: YOLO, DETR & Beyond
      • CLIP: Connecting Text and Images
      • Stable Diffusion & Image Generation
      • Multimodal RAG: Text + Images
    • Advanced NLP Specialization
      • Advanced NLP Specialization — Start Here
      • Named Entity Recognition (NER)
      • Machine Translation
      • Text Summarization: Extractive & Abstractive
      • Sentiment Analysis at Scale
      • Information Extraction from Documents

Advanced

  • Prompt Engineering
    • Assignment: Build an Advanced Prompt Engineering System
    • Setup
    • Example 1: Basic vs. Improved Prompt
    • Example 2: Few-Shot Learning
    • Example 3: Chain-of-Thought Reasoning
    • Example 4: System Prompts
    • Example 5: Structured Output
    • Key Takeaways
    • Next Steps
    • 1. Zero-Shot Prompting
    • 2. One-Shot Prompting
    • 3. Few-Shot Prompting
    • 4. Dynamic Few-Shot Selection
    • 5. Best Practices
    • Key Takeaways
    • Model Selection (December 2025)
    • Next Steps
    • 1. The Classic Example
    • 2. Zero-Shot CoT
    • 3. Few-Shot CoT
    • 4. Self-Consistency
    • 5. Structured CoT
    • 6. CoT for Code Debugging
    • 7. Least-to-Most Prompting
    • Best Practices
    • Key Takeaways
    • Next Steps
    • Setup
    • 1. Simple ReAct Example
    • 2. ReAct Agent
    • 3. Real Tools – Wikipedia Search
    • 4. More Complex Example
    • 5. Custom Tools
    • 6. Error Handling and Self-Correction
    • Best Practices
    • Key Takeaways
    • Limitations
    • Next Steps
    • Structured LLM Outputs & Programmatic Prompting (2025-2026)
    • Long-Context Strategies: Working with 128K–1M Token Windows
  • LLM Fine-Tuning
    • LLM Fine-tuning — Start Here
    • Dataset Preparation for LLM Fine-tuning
    • Supervised Fine-Tuning (SFT) — Complete Workflow
    • LoRA Fine-tuning Basics (December 2025)
    • QLoRA — Memory-Efficient Fine-Tuning on Consumer GPUs
    • DPO Alignment: Teaching Models to Be Helpful and Harmless
    • Evaluating Fine-Tuned LLMs
    • Deploying Fine-Tuned LLMs to Production
    • GRPO Reasoning Training - Training R1-Style Thinking Models (2025)
    • Unsloth - 2x-5x Faster Fine-Tuning with 80% Less VRAM (2025)
    • Quantization: GPTQ, AWQ, GGUF & bitsandbytes
    • RLHF & Constitutional AI: Alignment Training
  • Multimodal AI
    • Multimodal AI — Start Here
    • Audio & Speech
      • Whisper: Speech Recognition & Audio Understanding
      • Text-to-Speech: TTS with OpenAI, Coqui & Edge TTS
    • Image Generation
      • Stable Diffusion: Text-to-Image Generation
      • ControlNet: Precise Control Over Image Generation
    • Vision-Language Models
      • CLIP Basics: Zero-Shot Vision with CLIP
      • Vision-Language Models: GPT-4V, LLaVA & Gemini Vision
      • Multimodal RAG: Retrieval-Augmented Generation with Images
  • Local LLMs
    • AI Toolkit for VS Code
    • Local LLMs — Start Here
    • Setup
    • 1. Download and Run a Model
    • 8. CLI Usage (from terminal)
    • Tips & Best Practices
    • Key Takeaways
    • Limitations
    • Next Steps
    • Part 1: Major Open Source Model Families
    • Part 2: Model Family Deep Dives
    • 🎯 Key Takeaways
    • 📝 Practice Exercises
    • 🔗 Resources
    • Local RAG with Ollama
    • Local LLM Servers and APIs
    • Speculative Decoding: 2-3x Faster LLM Inference
  • AI Agents
    • AI Agents - Assignment
    • AI Agents - Challenges
    • AI Agents - Post-Quiz
    • AI Agents - Pre-Quiz
    • AI Agents — Start Here
    • Part 1: What is an AI Agent?
    • Part 2: Chatbot vs Agent
    • Part 4: Agent Design Patterns
    • 🎯 Summary
    • Setup
    • Part 1: Function Calling Basics
    • Part 2: Tool Schema Design
    • Part 4: Error Handling
    • Part 5: Advanced Patterns
    • Part 6: Best Practices Summary
    • 🎯 Final Knowledge Check
    • 🚀 Next Steps
    • Part 1: What is ReAct?
    • 🎯 Final Knowledge Check
    • 🚀 Next Steps
    • Part 1: Framework Overview (2026 Landscape)
    • Part 2: LangChain Agents
    • Part 3: LangGraph Workflows
    • Part 4: Memory Integration
    • Part 5: Framework Comparison
    • Part 6: Production Patterns
    • 🎯 Knowledge Check
    • 🚀 Next Steps
    • Part 1: Multi-Agent Basics
    • Part 2: Agent Coordination
    • Part 3: Role-Based Teams
    • Part 4: Communication Patterns
    • Part 5: Conflict Resolution
    • Part 6: A2A Protocol & Parallel Execution
    • Part 7: Production Systems
    • 🎯 Final Knowledge Check
    • 🚀 Next Steps
    • MCP — Model Context Protocol
    • OpenAI Agents SDK + LangGraph 1.0
    • Section A — OpenAI Agents SDK
    • Section B — LangGraph 1.0
    • Section C — Comparison and Production Guidance
    • Notebook 08: Working with Reasoning Models
    • Autonomous AI Agents in 2026
    • Notebook 10: Agent Evaluation

Supplementary

  • Model Evaluation
    • Assignment: Complete Model Evaluation Pipeline
    • Challenges: Model Evaluation & Metrics
    • Post-Quiz: Model Evaluation & Metrics
    • Pre-Quiz: Model Evaluation & Metrics
    • Model Evaluation — Start Here
    • Part 1: Confusion Matrix Basics
    • Part 2: Core Metrics
    • Part 3: ROC Curves & AUC
    • Part 4: Handling Imbalanced Data
    • Part 5: Multi-Class Metrics
    • Part 6: Choosing the Right Metric
    • 🎯 Knowledge Check
    • 🚀 Next Steps
    • Part 1: Core Regression Metrics
    • Part 2: Understanding Residuals
    • Part 3: R-Squared Explained
    • Part 4: Choosing the Right Metric
    • Part 5: Outlier Handling
    • Part 6: Advanced Metrics
    • 🎯 Knowledge Check
    • 📚 Summary
    • 🚀 Next Steps
    • Part 1: Introduction to LLM Evaluation
    • Part 2: BLEU Score
    • Part 3: ROUGE Metrics
    • Part 4: Perplexity
    • Part 5: Semantic Similarity (BERTScore)
    • Part 6: Human Evaluation
    • Part 7: RAG Evaluation
    • 🎯 Knowledge Check
    • 📚 Summary
    • 🚀 Next Steps
    • Part 1: Understanding Bias in AI
    • Part 2: Fairness Metrics
    • Part 3: Detecting Bias
    • Part 4: Mitigation Strategies
    • Part 5: Real-World Case Studies
    • Part 6: Fairness Toolkits
    • 🎯 Knowledge Check
    • 📚 Summary
    • 🚀 Next Steps
    • Part 1: Cross-Validation
    • Part 2: Comparing Multiple Models
    • Part 3: Statistical Significance Testing
    • Part 4: A/B Testing
    • Part 5: Multi-Objective Selection
    • Part 6: Model Selection Framework
    • 🎯 Knowledge Check
    • 📚 Summary
    • 🚀 Next Steps
  • Debugging & Troubleshooting
    • Assignment: Debug & Optimize a Broken ML Pipeline
    • Debugging & Troubleshooting Challenges
    • Post-Quiz: Debugging & Troubleshooting
    • Pre-Quiz: Debugging & Troubleshooting
    • Debugging & Troubleshooting — Start Here
    • Part 1: The Debugging Workflow
    • Part 2: Sanity Checks Checklist
    • Part 3: Baseline Models
    • Part 4: Debugging Checklist
    • Part 5: Logging and Instrumentation
    • 🎯 Key Takeaways
    • 📝 Practice Exercise
    • 🚀 Next Steps
    • Missing Data: The Silent Model Killer
    • Duplicate Detection: Preventing Data Leakage and Inflated Metrics
    • Outlier Detection: Distinguishing Signal from Noise
    • Label Noise Detection: When Your Ground Truth Lies
    • Distribution Shift Detection: When the World Changes Under Your Model
    • 🎯 Key Takeaways
    • 📝 Practice Exercise
    • CPU Profiling with cProfile: Finding Where Time Disappears
    • Vectorized Optimization: Replacing Loops with NumPy
    • Memory Profiling: Tracking Allocation and Leaks
    • Identifying Bottlenecks in ML Pipelines
    • Common Optimization Techniques for ML Code
    • Vectorization: Broadcasting Over Loops
    • Caching and Memoization: Trading Memory for Speed
    • Batch Processing: Amortizing Per-Call Overhead
    • 🎯 Key Takeaways
    • 📝 Optimization Checklist
    • Learning Curves: Diagnosing Bias vs. Variance
    • Overfitting vs. Underfitting: Visual Diagnosis with Polynomial Regression
    • Regularization Strategies: Constraining Model Complexity
    • Convergence Issues: When Gradient Descent Gets Lost
    • Model Complexity Trade-off: Validation Curves
    • 🎯 Key Takeaways
    • 📝 Debugging Checklist
    • Confusion Matrix Deep Dive: Beyond Aggregate Accuracy
    • Per-Class Error Analysis: Finding the Weakest Links
    • Failure Case Analysis: Learning from Mistakes
    • Confidence Analysis: Does the Model Know What It Does Not Know?
    • Error Analysis Report: Structured Communication of Findings
    • 🎯 Key Takeaways
    • 📝 Error Analysis Checklist
    • 🎉 Congratulations!
  • Low-Code AI Tools
    • Assignment: Low-Code ML Application
    • Challenges: Low-Code AI Tools
    • Post-Quiz: Low-Code AI Tools
    • Pre-Quiz: Low-Code AI Tools
    • Low-Code AI Tools — Start Here
    • Gradio Basics: From Python Function to Web Interface in Three Lines
    • Key Gradio Components
    • Image Classification Interface
    • Text Generation Interface: Controlling LLM Output
    • Advanced Layouts with Blocks: Beyond Simple Input-Output
    • Multi-Modal Interface: Combining Data Types
    • Sharing and Deployment: From Local to Global
    • Deployment Options
    • 🎯 Key Takeaways
    • 📝 Practice Exercises
    • 🔗 Resources
    • Streamlit Basics: Python Scripts that Become Web Apps
    • Running the App
    • ML Model Deployment App: Interactive Classification with Sidebar Controls
    • Session State: Persisting Data Across Reruns
    • Caching for Performance: Avoiding Redundant Computation
    • Interactive Data Dashboard: Filters, KPIs, and Multi-Tab Visualization
    • 🎯 Key Takeaways
    • 📝 Practice Exercises
    • 🔗 Resources
    • Part 1: Introduction to Hugging Face Spaces
    • Part 6: Advanced Space Configuration
    • 🎯 Key Takeaways
    • 📝 Practice Exercises
    • 🔗 Resources
    • Part 1: Introduction to AutoML
    • 🎯 Key Takeaways
    • 📝 Practice Exercises
    • 🔗 Resources
    • Data Preparation: Building a Realistic Churn Dataset
    • Model Training with AutoML: From Data to Tuned Model in Minutes
    • Build Gradio Interface: Making the Model Accessible
    • Create Deployable App Files: From Notebook to Production
    • Production Considerations: From Demo to Reliable System
    • 🎯 Key Takeaways
    • 📝 Project Extensions
    • 🎓 Final Exercise
    • 🏆 Congratulations!
  • AI Safety & Red Teaming
    • Assignment: Secure AI System Implementation
    • Challenges: AI Security & Red Teaming
    • Quiz: AI Safety & Red Teaming
    • AI Safety & Red Teaming — Start Here
    • Part 1: Understanding Prompt Injection Attacks
    • Summary & Best Practices
    • Practice Exercises
    • OpenAI Moderation API: Production-Grade Content Classification
    • Toxicity Detection with Detoxify: Local ML-Based Analysis
    • Custom Content Filters: Domain-Specific Safety Rules
    • Multi-Layer Content Moderation: Defense in Depth for Safety
    • Moderation Policies and Response Strategies: Beyond Binary Blocking
    • Production Implementation: Integrating All Components
    • Summary & Best Practices
    • Understanding PII Types: A Risk-Based Classification
    • Basic PII Detection with Regex: Fast Pattern Matching
    • Advanced PII Detection with Presidio: ML-Powered Entity Recognition
    • Anonymization Strategies: Choosing the Right Approach
    • Privacy Compliance: GDPR and CCPA Requirements
    • Production PII Protection Pipeline: End-to-End System
    • Summary & Best Practices
    • Understanding Bias Types: Where Unfairness Enters the ML Pipeline
    • Fairness Metrics: Mathematical Definitions of Equality
    • Visualizing Bias: Making Disparities Visible
    • Bias Mitigation Strategies: Pre-processing, In-processing, and Post-processing
    • Bias in LLMs: Detecting and Measuring Language Model Bias
    • Building Fairness-Aware Systems: Runtime Monitoring
    • Summary & Best Practices
    • Part 1: Red Team Methodology
    • Summary & Best Practices
  • Real-Time & Streaming AI
    • Real-Time Streaming — Start Here
    • Streaming LLM Responses
    • WebSocket Connections for Real-Time AI Chat
    • Streaming RAG Pipeline
    • Production-Grade Streaming Systems

Reference

  • Quizzes
    • Neural Networks - Post-Quiz
    • Neural Networks - Pre-Quiz
    • Retrieval-Augmented Generation (RAG) - Pre-Quiz
  • References & Hands-On Labs
    • Cloud Platform Labs & Resources ☁️
    • Microsoft Hands-On Labs 🧪
    • AI/ML Video Learning Resources 🎥
  • Glossary & Foundations
    • AI/ML Glossary

Research

  • Advanced Deep Learning
    • Advanced Deep Learning — Start Here
    • GAN Mathematics: Comprehensive Theory
    • Generative Adversarial Networks (GANs)
    • Wasserstein GAN (WGAN)
    • Variational Autoencoders (VAEs)
    • Neural Ordinary Differential Equations (Neural ODEs)
    • InfoGAN: Information-Maximizing Generative Adversarial Networks - Comprehensive Theory
    • Vision Transformers (ViT)
    • 1. Motivation: Multi-Scale Latent Representations
    • 2. ELBO for Hierarchical VAE
    • Summary
    • Conditional GANs (cGAN): Comprehensive Theory
    • 1. Motivation: Discrete Latent Spaces
    • 2. Vector Quantization Layer
    • Summary
    • Advanced Vector Quantized Variational Autoencoders (VQ-VAE): Theory and Practice
    • 1. Motivation: Exact Likelihood
    • 3. Composing Flows
    • 6. Modern Flow Architectures
    • Summary
    • Advanced Normalizing Flows Theory
    • 1. Motivation: Iterative Refinement
    • 2. Forward Diffusion Process
    • 3. Reverse Process & Training
    • 4. Sampling (Reverse Process)
    • Summary
    • Advanced Diffusion Models Theory
    • 1. BERT vs GPT
    • 1.5. Masked Language Modeling: Deep Dive
    • 2.5. Segment Embeddings and Special Tokens
    • 3.5. BERT Training: Advanced Techniques
    • Summary
    • 1. GPT vs BERT
    • 1.5. Causal Masking: Mathematical Foundation
    • 2.5. Positional Encoding: Theory and Variants
    • 3.5. Scaling Laws for Language Models
    • 4.5. Advanced Generation Strategies: Complete Analysis
    • Summary
    • 1. Attention Complexity Problem
    • 2. Linformer: Low-Rank Attention
    • 3. Performer: Kernel Approximation
    • Summary
    • Advanced Efficient Transformers Theory
    • 1. Message Passing Framework
    • 2. Graph Convolutional Network (GCN)
    • Advanced Message Passing Theory
    • 3. Graph Attention Network (GAT)
    • Summary
    • Advanced Graph Neural Networks Theory
    • 1. Meta-Learning Problem
    • 2. MAML Algorithm
    • Summary
    • Advanced Meta-Learning Theory
    • Advanced Meta-Learning and MAML Theory
    • 1. Few-Shot Classification
    • 2. Algorithm
    • Summary
    • Advanced Prototypical Networks Theory
    • Neural Radiance Fields (NeRF): Comprehensive Theory
    • 1. Style-Based Generator
    • Summary
    • Advanced StyleGAN: Mathematical Foundations and Architecture Deep Dive
    • 1. Contrastive Learning Framework
    • Summary
    • Advanced Contrastive Learning Theory
    • Advanced Adversarial Robustness Theory
    • 1. Adversarial Examples
    • 5. PGD Attack
    • Summary
    • 1. Knowledge Distillation
    • Summary
    • Advanced Knowledge Distillation Theory
    • 1. Point Cloud Basics
    • 2. T-Net (Transformation Network)
    • 3. PointNet Architecture
    • Summary
    • Advanced Point Cloud Networks Theory
    • 1. CycleGAN Theory
    • Summary
    • 1. Progressive Growing
    • Summary
    • Advanced Neural Network Interpretability Theory
    • 1. GradCAM Theory
    • Summary
    • Advanced Curriculum Learning Theory
    • 1. Curriculum Learning
    • Summary
    • 1. Catastrophic Forgetting
    • Summary
    • Advanced Continual Learning Theory
    • Advanced Continual Learning Theory
    • Advanced Continual Learning: Mathematical Foundations and Modern Approaches
    • Advanced Neural Architecture Search Theory
    • 1. DARTS: Differentiable Architecture Search
    • Summary
    • Advanced Neural Architecture Search Theory
    • Advanced Neural Architecture Search: Mathematical Foundations and Modern Methods
    • 1. Bahdanau Attention (Additive)
    • 2. Luong Attention (Multiplicative)
    • 3. Scaled Dot-Product Attention
    • 4. Multi-Head Attention
    • Summary
    • Advanced Attention Mechanisms: Mathematical Foundations and Modern Architectures
    • 1. Memory Networks Concept
    • 2. Content-Based Addressing
    • Summary
    • Advanced Memory Networks Theory
    • Advanced Memory Networks: Mathematical Foundations and Modern Architectures
    • 1. Capsule Networks Concept
    • 2. Dynamic Routing
    • 5. Margin Loss
    • Summary
    • Advanced Capsule Networks Theory
    • Advanced Capsule Networks Theory
    • Advanced Capsule Networks: Mathematical Foundations and Modern Architectures
    • 1. Score Matching
    • 3. Langevin Dynamics Sampling
    • 6. Annealed Langevin Dynamics
    • Summary
    • Advanced Score-Based Generative Models Theory
    • Advanced Score-Based Generative Models: Mathematical Foundations and Modern Architectures
    • 1. Energy-Based Models
    • 2. Contrastive Divergence
    • Summary
    • Advanced Energy-Based Models Theory
    • Advanced Energy-Based Models: Mathematical Foundations and Modern Architectures
    • 1. Mixture of Experts Concept
    • Summary
    • Advanced Mixture of Experts: Mathematical Foundations and Modern Architectures
    • 1. Implicit Neural Representations
    • Summary
    • Advanced Implicit Neural Representations Theory
    • 1. Gaussian Process Theory
    • 1.5. Gaussian Process Theory: Deep Mathematical Foundations
    • 7.5. Sparse Gaussian Processes: Scaling to Large Data
    • Summary
    • Advanced GP Topics and Extensions
    • Advanced Gaussian Processes Theory
    • 1. Bayesian Neural Networks
    • Bayesian Neural Networks: Deep Theory and Variational Inference
    • Summary
    • Advanced Bayesian Neural Networks Theory
  • Reinforcement Learning
    • Reinforcement Learning — Start Here
    • 01: Markov Decision Processes (MDPs)
    • 02: Value-Based Methods (Q-Learning)
    • 03: Deep Q-Networks (DQN)
    • 04: Policy-Based Methods (REINFORCE)
    • 05: Advanced Topics & Real-World Applications
    • 06: Practical Exercises & Implementations
  • Time Series Analysis & Forecasting
    • Time Series Analysis — Start Here
    • 01: Time Series Fundamentals
    • 02: Classical Statistical Methods
    • 03: Facebook Prophet
    • 04: Deep Learning for Time Series
    • 05: Advanced Techniques & Applications
    • 06: Practical Applications & Exercises
  • Causal Inference
    • Causal Inference — Start Here
    • 01: Causal Fundamentals
    • 02: Causal Graphs & DAGs
    • 03: Experimental Design
    • 04: Observational Methods
    • 05: Advanced Topics & Applications
    • 🎯 Quasi-Experimental Designs

Production

  • Practical Data Science
    • Data Science Interview Prep: The 30 Questions That Actually Come Up
    • Data Science Interview Prep — Part 2: Q16 to Q30
    • Practical Data Science
    • Computer Vision
      • Image Processing Basics: NumPy Arrays, PIL, and Computer Vision Fundamentals
      • CNNs From Scratch: Understanding Convolution, Pooling, and Classification
      • Transfer Learning: Leveraging Pretrained Models for Custom Image Tasks
      • Object Detection: From Bounding Boxes to Modern Detectors
      • Image Segmentation: Pixel-Level Understanding
    • Deep Learning & NLP
      • Transformers from Scratch: Self-Attention & Positional Encoding
      • BERT Text Classification: Fine-Tuning Transformers on Your Own Data
      • LLM Application Patterns: Building Production-Grade AI Features
      • Text Preprocessing: From Raw Text to Features
      • LLM Fine-Tuning with LoRA and QLoRA
    • Machine Learning
      • sklearn Pipelines: The Right Way to Build ML Workflows
      • Model Selection: Cross-Validation, Learning Curves & Bias-Variance
      • Ensemble Methods: Bagging, Boosting & Stacking
      • Imbalanced Datasets: Handling Class Imbalance Properly
      • Model Interpretability: SHAP, Permutation Importance & Partial Dependence
      • End-to-End ML Project: Customer Churn Prediction
    • Python for Data Science
      • Pandas Fundamentals: The Operations Every Data Scientist Must Know
      • Exploratory Data Analysis: A Systematic Framework
      • Data Visualization: From Exploratory Plots to Publication-Quality Figures
      • Data Cleaning Pipelines: From Messy Data to Model-Ready Features
      • Feature Engineering: Turning Raw Data into Model Fuel
    • Recommender Systems & Causal Inference
      • Collaborative Filtering: Building Recommender Systems from User Behavior
      • Content-Based Filtering: Recommending by Item Similarity
      • Neural Collaborative Filtering: Deep Learning for Recommendations
      • Causal Inference: Moving Beyond Correlation
      • Difference-in-Differences: Causal Inference from Natural Experiments
      • Building an A/B Testing Platform
    • Solutions
      • Solutions: Computer Vision Track
      • Solutions: Deep Learning & NLP Track
      • Solutions: Machine Learning Track
      • Solutions: Python & Data Science Track
      • Solutions: Recommender Systems & Causal Inference Track
      • Solutions: SQL & Data Engineering Track
      • Solutions: Statistics & MLOps Track
      • Solutions: Time Series & Forecasting Track
    • SQL & Data Engineering
      • Advanced SQL: Window Functions, CTEs, and Query Patterns That Actually Matter
      • SQL Query Optimization: From Slow to Fast in 10 Patterns
      • Data Pipelines with Airflow: DAGs, Operators, and Production Patterns
      • PySpark Fundamentals: Distributed Data Processing for Large Datasets
      • dbt: Data Modeling for Analytics Engineering
      • Streaming Data: Kafka, Windowed Aggregations, and Real-Time Pipelines
    • Statistics & MLOps
      • Hypothesis Testing: The Statistics Behind A/B Tests and Decisions
      • Bayesian Thinking: Updating Beliefs with Data
      • Model Deployment with FastAPI: From Notebook to Production API
      • ML Monitoring & Drift Detection: Keeping Models Healthy in Production
      • Feature Stores: From Training to Production Without Data Leakage
    • Time Series Forecasting
      • Time Series Fundamentals: Decomposition, Stationarity, and Autocorrelation
      • ARIMA & SARIMA: Statistical Forecasting for Practitioners
      • Prophet: Scalable Forecasting for Business Time Series
      • LSTM for Time Series: Sequence Modeling with Deep Learning
      • Anomaly Detection: Finding the Signal in Noisy Time Series
      • Forecasting Competition: ARIMA vs Prophet vs LSTM
  • AI Hardware & Validation
    • Section 1: Hardware Validation
    • Section 2: Kernel Validation
    • Section 3: Framework Validation
    • Section 4: Model Performance Validation
    • Section 5: End-to-End Pipeline Validation
    • Section 6: Distributed Training Validation
    • Section 7: Datacenter Validation
    • Section 8: Regression & Release Validation
    • Chapter 9: Industry AI Benchmarking & Performance Analysis
    • Part 1 — LLM Performance Metrics: What Gets Measured
    • Part 2 — API Performance Benchmarking
    • Part 3 — Hardware Benchmarking: AA-SLT (System Load Test)
    • Part 4 — Hardware Benchmarking: AA-AgentPerf
    • Part 5 — Intelligence Benchmarking
    • Part 6 — Multi-Modal Benchmarking
    • Part 7 — Other Industry Benchmarks
    • Exercises
    • Key Takeaways
    • Lab 01: Hardware Validation
    • Lab 02: Kernel Validation
    • Lab 03: Model Performance Validation
    • Lab 04: Regression & Release Validation Suite
    • Lab 05: Distributed Training Validation
    • Lab 06: Framework Validation
    • Lab 07 — GPGPU Backends: CoreML · DirectML · Vulkan
    • Part 1 — CoreML (Apple)
    • Part 2 — DirectML (Microsoft / Windows)
    • Part 3 — Vulkan (Cross-Platform)
    • Part 4 — Cross-Backend Parity Validation
    • Part 5 — Exercises
    • Key Takeaways
    • Lab 08 — Industry Benchmarking: Hands-On
    • Part 1 — TTFT & Output Speed Measurement
    • Part 2 — Mini AA-SLT (System Load Test)
    • Part 3 — SLO-Based Capacity Planning (AA-AgentPerf Style)
    • Part 4 – Hardware Comparison Dashboard
    • Part 5 — Mini Intelligence Eval Runner
    • Exercises
    • Key Takeaways
  • Inference Optimization & Model Serving
    • vLLM Quickstart: High-Throughput Model Serving

Developer Tools

  • AI-Powered Development with VS Code & GitHub Copilot
    • AI Coding Tools for ML Engineers (March 2026)
    • VS Code AI Setup Guide
    • MCP Deep Dive: Model Context Protocol
    • GitHub Copilot Customization Guide
    • VS Code + GitHub Copilot Workflows
    • Build a Simple MCP Server in Python
Back to top
View this page
Edit this page

Microsoft Open Source Code of Conduct¶

This project has adopted the Microsoft Open Source Code of Conduct.

Resources:

  • Microsoft Open Source Code of Conduct

  • Microsoft Code of Conduct FAQ

  • Contact opencode@microsoft.com with questions or concerns

Next
Data Science for Beginners - A Curriculum
Previous
Contributing
Copyright © MIT License 2026, Pavan Mudigonda
v0.1.0