Lesson Catalog
Every lesson across all 20 phases. Search, filter, sort.
Showing 273 of 273 lessons
| Phase | Lesson | Status |
|---|---|---|
| 00 | Dev Environment | complete |
| 00 | Git & Collaboration | complete |
| 00 | GPU Setup & Cloud | complete |
| 00 | APIs & Keys | complete |
| 00 | Jupyter Notebooks | complete |
| 00 | Python Environments | complete |
| 00 | Docker for AI | complete |
| 00 | Editor Setup | complete |
| 00 | Data Management | complete |
| 00 | Terminal & Shell | complete |
| 00 | Linux for AI | complete |
| 00 | Debugging & Profiling | complete |
| 01 | Linear Algebra Intuition | complete |
| 01 | Vectors, Matrices & Operations | complete |
| 01 | Matrix Transformations & Eigenvalues | complete |
| 01 | Calculus for ML: Derivatives & Gradients | complete |
| 01 | Chain Rule & Automatic Differentiation | complete |
| 01 | Probability & Distributions | complete |
| 01 | Bayes' Theorem & Statistical Thinking | complete |
| 01 | Optimization: Gradient Descent Family | complete |
| 01 | Information Theory: Entropy, KL Divergence | complete |
| 01 | Dimensionality Reduction: PCA, t-SNE, UMAP | complete |
| 01 | Singular Value Decomposition | complete |
| 01 | Tensor Operations | complete |
| 01 | Numerical Stability | complete |
| 01 | Norms & Distances | complete |
| 01 | Statistics for ML | complete |
| 01 | Sampling Methods | complete |
| 01 | Linear Systems | complete |
| 01 | Convex Optimization | complete |
| 01 | Complex Numbers for AI | complete |
| 01 | The Fourier Transform | complete |
| 01 | Graph Theory for ML | complete |
| 01 | Stochastic Processes | complete |
| 02 | What Is Machine Learning | complete |
| 02 | Linear Regression from Scratch | complete |
| 02 | Logistic Regression & Classification | complete |
| 02 | Decision Trees & Random Forests | complete |
| 02 | Support Vector Machines | complete |
| 02 | KNN & Distance Metrics | complete |
| 02 | Unsupervised Learning: K-Means, DBSCAN | complete |
| 02 | Feature Engineering & Selection | complete |
| 02 | Model Evaluation: Metrics, Cross-Validation | complete |
| 02 | Bias, Variance & the Learning Curve | complete |
| 02 | Ensemble Methods: Boosting, Bagging, Stacking | complete |
| 02 | Hyperparameter Tuning | complete |
| 02 | ML Pipelines & Experiment Tracking | complete |
| 02 | Naive Bayes | complete |
| 02 | Time Series Fundamentals | complete |
| 02 | Anomaly Detection | complete |
| 02 | Handling Imbalanced Data | complete |
| 02 | Feature Selection | complete |
| 03 | The Perceptron: Where It All Started | complete |
| 03 | Multi-Layer Networks & Forward Pass | complete |
| 03 | Backpropagation from Scratch | complete |
| 03 | Activation Functions: ReLU, Sigmoid, GELU & Why | complete |
| 03 | Loss Functions: MSE, Cross-Entropy, Contrastive | complete |
| 03 | Optimizers: SGD, Momentum, Adam, AdamW | complete |
| 03 | Regularization: Dropout, Weight Decay, BatchNorm | complete |
| 03 | Weight Initialization & Training Stability | complete |
| 03 | Learning Rate Schedules & Warmup | complete |
| 03 | Build Your Own Mini Framework | complete |
| 03 | Introduction to PyTorch | complete |
| 03 | Introduction to JAX | complete |
| 03 | Debugging Neural Networks | complete |
| 04 | Image Fundamentals: Pixels, Channels, Color Spaces | complete |
| 04 | Convolutions from Scratch | complete |
| 04 | CNNs: LeNet to ResNet | complete |
| 04 | Image Classification | complete |
| 04 | Transfer Learning & Fine-Tuning | complete |
| 04 | Object Detection — YOLO from Scratch | complete |
| 04 | Semantic Segmentation — U-Net | complete |
| 04 | Instance Segmentation — Mask R-CNN | complete |
| 04 | Image Generation — GANs | complete |
| 04 | Image Generation — Diffusion Models | complete |
| 04 | Stable Diffusion — Architecture & Fine-Tuning | complete |
| 04 | Video Understanding — Temporal Modeling | complete |
| 04 | 3D Vision: Point Clouds, NeRFs | complete |
| 04 | Vision Transformers (ViT) | complete |
| 04 | Real-Time Vision: Edge Deployment | complete |
| 04 | Build a Complete Vision Pipeline | complete |
| 04 | Self-Supervised Vision — SimCLR, DINO, MAE | complete |
| 04 | Open-Vocabulary Vision — CLIP | complete |
| 04 | OCR & Document Understanding | complete |
| 04 | Image Retrieval & Metric Learning | complete |
| 04 | Keypoint Detection & Pose Estimation | complete |
| 04 | 3D Gaussian Splatting from Scratch | complete |
| 04 | Diffusion Transformers & Rectified Flow | complete |
| 04 | SAM 3 & Open-Vocabulary Segmentation | complete |
| 04 | Vision-Language Models (ViT-MLP-LLM) | complete |
| 04 | Monocular Depth & Geometry Estimation | complete |
| 04 | Multi-Object Tracking & Video Memory | complete |
| 04 | World Models & Video Diffusion | complete |
| 05 | Text Processing: Tokenization, Stemming, Lemmatization | planned |
| 05 | Bag of Words, TF-IDF & Text Representation | planned |
| 05 | Word Embeddings: Word2Vec from Scratch | planned |
| 05 | GloVe, FastText & Subword Embeddings | planned |
| 05 | Sentiment Analysis | planned |
| 05 | Named Entity Recognition (NER) | planned |
| 05 | POS Tagging & Syntactic Parsing | planned |
| 05 | Text Classification — CNNs & RNNs for Text | planned |
| 05 | Sequence-to-Sequence Models | planned |
| 05 | Attention Mechanism — The Breakthrough | planned |
| 05 | Machine Translation | planned |
| 05 | Text Summarization | planned |
| 05 | Question Answering Systems | planned |
| 05 | Information Retrieval & Search | planned |
| 05 | Topic Modeling: LDA, BERTopic | planned |
| 05 | Text Generation | planned |
| 05 | Chatbots: Rule-Based to Neural | planned |
| 05 | Multilingual NLP | planned |
| 06 | Audio Fundamentals: Waveforms, Sampling, FFT | planned |
| 06 | Spectrograms, Mel Scale & Audio Features | planned |
| 06 | Audio Classification | planned |
| 06 | Speech Recognition (ASR) | planned |
| 06 | Whisper: Architecture & Fine-Tuning | planned |
| 06 | Speaker Recognition & Verification | planned |
| 06 | Text-to-Speech (TTS) | planned |
| 06 | Voice Cloning & Voice Conversion | planned |
| 06 | Music Generation | planned |
| 06 | Audio-Language Models | planned |
| 06 | Real-Time Audio Processing | planned |
| 06 | Build a Voice Assistant Pipeline | planned |
| 07 | Why Transformers: The Problems with RNNs | planned |
| 07 | Self-Attention from Scratch | complete |
| 07 | Multi-Head Attention | planned |
| 07 | Positional Encoding: Sinusoidal, RoPE, ALiBi | planned |
| 07 | The Full Transformer: Encoder + Decoder | planned |
| 07 | BERT — Masked Language Modeling | planned |
| 07 | GPT — Causal Language Modeling | planned |
| 07 | T5, BART — Encoder-Decoder Models | planned |
| 07 | Vision Transformers (ViT) | planned |
| 07 | Audio Transformers — Whisper Architecture | planned |
| 07 | Mixture of Experts (MoE) | planned |
| 07 | KV Cache, Flash Attention & Inference Optimization | planned |
| 07 | Scaling Laws | planned |
| 07 | Build a Transformer from Scratch | planned |
| 08 | Generative Models: Taxonomy & History | planned |
| 08 | Autoencoders & VAE | planned |
| 08 | GANs: Generator vs Discriminator | planned |
| 08 | Conditional GANs & Pix2Pix | planned |
| 08 | StyleGAN | planned |
| 08 | Diffusion Models — DDPM from Scratch | planned |
| 08 | Latent Diffusion & Stable Diffusion | planned |
| 08 | ControlNet, LoRA & Conditioning | planned |
| 08 | Inpainting, Outpainting & Editing | planned |
| 08 | Video Generation | planned |
| 08 | Audio Generation | planned |
| 08 | 3D Generation | planned |
| 08 | Flow Matching & Rectified Flows | planned |
| 08 | Evaluation: FID, CLIP Score | planned |
| 09 | MDPs, States, Actions & Rewards | planned |
| 09 | Dynamic Programming | planned |
| 09 | Monte Carlo Methods | planned |
| 09 | Q-Learning, SARSA | planned |
| 09 | Deep Q-Networks (DQN) | planned |
| 09 | Policy Gradients — REINFORCE | planned |
| 09 | Actor-Critic — A2C, A3C | planned |
| 09 | PPO | planned |
| 09 | Reward Modeling & RLHF | planned |
| 09 | Multi-Agent RL | planned |
| 09 | Sim-to-Real Transfer | planned |
| 09 | RL for Games | planned |
| 10 | Tokenizers: BPE, WordPiece, SentencePiece | complete |
| 10 | Building a Tokenizer from Scratch | complete |
| 10 | Data Pipelines for Pre-Training | complete |
| 10 | Pre-Training a Mini GPT (124M) | complete |
| 10 | Distributed Training, FSDP, DeepSpeed | complete |
| 10 | Instruction Tuning — SFT | complete |
| 10 | RLHF — Reward Model + PPO | complete |
| 10 | DPO — Direct Preference Optimization | complete |
| 10 | Constitutional AI | planned |
| 10 | Evaluation — Benchmarks, Evals | complete |
| 10 | Quantization: INT8, GPTQ, AWQ, GGUF | complete |
| 10 | Inference Optimization | complete |
| 10 | Building a Complete LLM Pipeline | planned |
| 10 | Open Models: Architecture Walkthroughs | planned |
| 11 | Prompt Engineering: Techniques & Patterns | complete |
| 11 | Few-Shot, CoT, Tree-of-Thought | complete |
| 11 | Structured Outputs | complete |
| 11 | Embeddings & Vector Representations | complete |
| 11 | Context Engineering | complete |
| 11 | RAG: Retrieval-Augmented Generation | complete |
| 11 | Advanced RAG: Chunking, Reranking | complete |
| 11 | Fine-Tuning with LoRA & QLoRA | complete |
| 11 | Function Calling & Tool Use | complete |
| 11 | Evaluation & Testing | complete |
| 11 | Caching, Rate Limiting & Cost | complete |
| 11 | Guardrails & Safety | complete |
| 11 | Building a Production LLM App | complete |
| 12 | Multimodal Representations | planned |
| 12 | CLIP: Vision + Language | planned |
| 12 | Vision-Language Models | planned |
| 12 | Audio-Language Models | planned |
| 12 | Document Understanding | planned |
| 12 | Video-Language Models | planned |
| 12 | Multimodal RAG | planned |
| 12 | Multimodal Agents | planned |
| 12 | Text-to-Image Pipelines | planned |
| 12 | Text-to-Video Pipelines | planned |
| 12 | Any-to-Any Models | planned |
| 13 | Function Calling Deep Dive | planned |
| 13 | Tool Use Patterns | planned |
| 13 | MCP: Model Context Protocol | planned |
| 13 | Building MCP Servers | planned |
| 13 | Building MCP Clients | planned |
| 13 | MCP Resources, Prompts & Sampling | planned |
| 13 | Structured Output Schemas | planned |
| 13 | API Design for AI | planned |
| 13 | Browser Automation & Web Agents | planned |
| 13 | Build a Complete Tool Ecosystem | planned |
| 14 | The Agent Loop | complete |
| 14 | Tool Dispatch & Registration | planned |
| 14 | Planning: TodoWrite, DAGs | planned |
| 14 | Memory: Short-Term, Long-Term, Episodic | planned |
| 14 | Context Window Management | planned |
| 14 | Context Compression & Summarization | planned |
| 14 | Subagents: Delegation | planned |
| 14 | Skills & Knowledge Loading | planned |
| 14 | Permissions, Sandboxing & Safety | planned |
| 14 | File-Based Task Systems | planned |
| 14 | Background Task Execution | planned |
| 14 | Error Recovery & Self-Healing | planned |
| 14 | Hooks: PreToolUse, PostToolUse | planned |
| 14 | Eval-Driven Agent Development | planned |
| 14 | Build a Complete AI Agent | planned |
| 15 | What Makes a System Autonomous | planned |
| 15 | Autonomous Loops | planned |
| 15 | Self-Healing Agents | planned |
| 15 | AutoResearch: Autonomous Research | planned |
| 15 | Eval-Driven Loops | planned |
| 15 | Human-in-the-Loop | planned |
| 15 | Continuous Agents | planned |
| 15 | Cost-Aware Autonomous Systems | planned |
| 15 | Monitoring & Observability | planned |
| 15 | Safety Boundaries | planned |
| 15 | Build an Autonomous Coding Agent | planned |
| 16 | Why Multi-Agent | complete |
| 16 | Agent Teams: Roles & Delegation | planned |
| 16 | Communication Protocols | complete |
| 16 | Shared State & Coordination | planned |
| 16 | Message Passing & Mailboxes | planned |
| 16 | Task Markets | planned |
| 16 | Consensus Algorithms | planned |
| 16 | Swarm Intelligence | planned |
| 16 | Agent Economies | planned |
| 16 | Worktree Isolation | planned |
| 16 | Hierarchical Swarms | planned |
| 16 | Self-Organizing Systems | planned |
| 16 | DAG-Based Orchestration | planned |
| 16 | Build an Autonomous Swarm | planned |
| 17 | Model Serving | complete |
| 17 | Docker for AI Workloads | complete |
| 17 | Kubernetes for AI | complete |
| 17 | Edge Deployment: ONNX, WASM | planned |
| 17 | Observability | planned |
| 17 | Cost Optimization | planned |
| 17 | CI/CD for ML | planned |
| 17 | A/B Testing & Feature Flags | planned |
| 17 | Data Pipelines | planned |
| 17 | Security: Red Teaming, Defense | planned |
| 17 | Build a Production AI Platform | planned |
| 18 | AI Ethics: Bias, Fairness | planned |
| 18 | Alignment: What & Why | planned |
| 18 | Red Teaming & Adversarial Testing | planned |
| 18 | Responsible AI Frameworks | planned |
| 18 | Privacy: Differential Privacy, FL | planned |
| 18 | Interpretability: SHAP, Attention | planned |
| 19 | 🤖 Build a Mini GPT & Chat Interface | planned |
| 19 | 🔍 Build a Multimodal RAG System | planned |
| 19 | 🧪 Build an Autonomous Research Agent | planned |
| 19 | 👥 Build a Multi-Agent Dev Team | planned |
| 19 | 🚀 Build a Production AI Platform | planned |