Learning Path
Click any topic to start. Follow the numbers for the recommended order, or jump to whatever catches your eye.
Foundations
Core concepts and fundamentals
What is AI & Machine Learning?
The big picture — types of AI, how machines learn
Math Intuition for AI
Vectors, matrices, gradients — visual intuition, no proofs
How Computers Understand Text
NLP basics, preprocessing, bag-of-words, TF-IDF
Tokenization
Breaking text into pieces — BPE, WordPiece, SentencePiece
Word Embeddings & Vector Spaces
Turning words into numbers — Word2Vec, GloVe, similarity
Classical Machine Learning
Regression, trees, SVM, clustering — how algorithms think
Deep Learning Core
Neural networks and modern architectures
Neural Networks & Backpropagation
Perceptrons, layers, how a network learns step by step
Training Deep Networks
Loss functions, optimizers, regularization, overfitting
CNNs — How AI Sees Images
Convolution, filters, pooling, feature maps, transfer learning
RNNs & LSTMs — Sequence Memory
Vanishing gradients, LSTM gates, the precursor to transformers
Attention Mechanism
Self-attention, multi-head attention, how models learn to focus
Transformer Architecture
Encoder, decoder, positional encoding — full animated walkthrough
LLMs & Modern AI
Large language models and transformers
Large Language Models
GPT, BERT, Llama, Claude — scaling laws and emergent abilities
Pre-training & Fine-tuning
How LLMs learn from the internet, SFT, transfer learning
RLHF & Alignment
Teaching AI human preferences — reward models, DPO, Constitutional AI
Prompt Engineering
Zero-shot, few-shot, chain-of-thought, structured outputs
PEFT — LoRA, QLoRA & Adapters
Training 0.1% of parameters — efficient fine-tuning
Multimodal AI
Vision-language models, diffusion models, cross-modal understanding
Production
Deployment and optimization
Model Internals
RoPE, MoE, GQA — inside Llama, Mistral, Gemma
Quantization & Compression
INT8/INT4, GPTQ, AWQ, GGUF — quality vs size trade-offs
Inference & Serving
vLLM, KV-cache, paged attention, Flash Attention, batching
Evaluation & Benchmarks
MMLU, HumanEval, BLEU, ROUGE — measuring if AI works
MLOps & Deployment
Pipelines, monitoring, drift detection — notebook to production
Agents & Frontier
Advanced topics and emerging research
RAG & Vector Search
Retrieval-augmented generation, vector databases, chunking
Agents & Reasoning
ReAct, chain-of-thought, planning, tool use, function calling
Agent Frameworks
LangChain, LlamaIndex, CrewAI, Claude Agent SDK
Reasoning Models & Extended Thinking
o1/o3-style reasoning, test-time compute, self-verification
AI Safety & Ethics
Hallucinations, bias, prompt injection, responsible AI
State Space Models & New Architectures
Mamba, S4, RWKV — what comes after transformers?
Building Production AI Systems
End-to-end capstone — data to deployment with guardrails