Master Machine Learning
From the math that matters to models that deploy - supervised, unsupervised, neural networks, and the engineering around all of it.
15 Modules. One Complete Track.
From foundations to cutting-edge research. Start free, go deep.
ML Foundations
The core building blocks - what ML is, how it learns, and how to measure it rigorously.
What you'll master
- Bias-Variance Tradeoff
- Supervised, Unsupervised & RL
- Evaluation Metrics (Regression & Classification)
- Cross-Validation & Train/Val/Test Split
- Probabilistic View of ML
- Statistical Learning Theory
12 lessons
Start for Free →
Linear Models
Linear and logistic regression from scratch - gradient descent, regularization, MLE, and GLMs.
What you'll master
- Linear Regression Internals
- Gradient Descent & Mini-Batch SGD
- Logistic Regression Deep Dive
- Regularization - L1, L2, ElasticNet
- Maximum Likelihood Estimation
- Generalized Linear Models
8 lessons
Start for Free →
Tree Models & Ensembles
Decision trees, random forests, gradient boosting, and XGBoost - from splits to SHAP values.
What you'll master
- Decision Trees Internals
- Bagging & Random Forests
- Gradient Boosting from Scratch
- XGBoost Deep Dive
- Feature Importance & SHAP
9 lessons
Start for Free →
Neural Networks
Build neural networks from first principles - backprop, activations, optimizers, and regularization.
What you'll master
- Perceptron & MLP
- Backpropagation from Scratch
- Activation Functions
- Weight Initialization
- Batch Normalization & Dropout
- Optimizers - Adam, SGD, RMSProp
10 lessons
Start for Free →
Computer Vision
CNNs, modern architectures, transfer learning, object detection, and semantic segmentation.
What you'll master
- Convolutional Neural Networks
- Pooling, Strides & Padding
- ResNet & EfficientNet
- Transfer Learning
- Object Detection - YOLO & R-CNN
- Semantic Segmentation
8 lessons
Start for Free →
Sequences & Time Series
RNNs, LSTMs, GRUs, seq2seq, attention, and time series forecasting for production systems.
What you'll master
- RNNs & Vanishing Gradients
- LSTM & GRU Deep Dive
- Seq2Seq & Encoder-Decoder
- Attention Mechanisms
- Time Series Forecasting
6 lessons
Start for Free →
Unsupervised Learning
Clustering, dimensionality reduction, autoencoders, and anomaly detection without labels.
What you'll master
- K-Means Clustering
- Hierarchical & DBSCAN
- PCA & t-SNE
- Autoencoders
- Anomaly Detection
8 lessons
Start for Free →
Recommender Systems
Collaborative filtering, matrix factorization, content-based, and neural recommenders.
What you'll master
- Collaborative Filtering
- Matrix Factorization
- Content-Based Filtering
- Neural Recommender Systems
- Evaluation for RecSys
7 lessons
Start for Free →
ML Engineering with Python
NumPy, Pandas, scikit-learn pipelines, PyTorch training loops, and the Hugging Face ecosystem.
What you'll master
- NumPy for ML
- Pandas for ML
- Scikit-Learn Pipelines
- PyTorch Foundations & Training Loop
- Hugging Face Ecosystem
8 lessons
Start for Free →
ML System Design
Frame ML problems, design data pipelines, model serving, monitoring, and end-to-end case studies.
What you'll master
- Framing ML Problems
- Data Pipeline Design
- Feature Stores
- Model Serving & Deployment
- Monitoring & Observability
8 lessons
Start for Free →
Reinforcement Learning
MDPs, dynamic programming, Q-learning, DQN, policy gradients, and RLHF for LLMs.
What you'll master
- MDPs & the RL Framework
- Dynamic Programming
- Q-Learning & SARSA
- Deep Q-Networks (DQN)
- Policy Gradient Methods
- RLHF for Language Models
10 lessons
Start for Free →
Explainability & Interpretability
SHAP, LIME, attention maps, mechanistic interpretability, and model audit frameworks.
What you'll master
- Interpretability vs Explainability
- SHAP Values in Depth
- LIME for Local Explanations
- Attention-Based Explanations
- Model Audit & Fairness
9 lessons
Start for Free →
Graph Neural Networks
GCN, GAT, GraphSAGE, message passing, graph classification, and link prediction.
What you'll master
- Why Graphs for ML
- Graph Representation
- Graph Convolutional Networks
- Graph Attention Networks
- GraphSAGE & Inductive Learning
8 lessons
Start for Free →
Bayesian Machine Learning
Bayesian inference, Gaussian processes, variational inference, and uncertainty quantification.
What you'll master
- Probabilistic Perspective on ML
- Bayesian Inference
- Gaussian Processes
- Variational Inference
- Uncertainty Quantification
8 lessons
Start for Free →
Diffusion Models
Score matching, DDPM, DDIM, latent diffusion, and classifier-free guidance from first principles.
What you'll master
- Generative Models Overview
- Score Matching & Diffusion
- DDPM & DDIM
- Latent Diffusion Models
- Classifier-Free Guidance
9 lessons
Start for Free →
Ready to master the math behind the models?
From linear algebra to production ML systems - no skipped steps.
Start Learning Free →