🤖 Artificial Intelligence, Machine Learning & LLMs: Master Curriculum Index
Welcome to the Artificial Intelligence, Machine Learning & Large Language Models master knowledge base. This curriculum provides software engineers with an end-to-end, rigorous understanding of modern AI systems—from classical statistical learning and deep neural networks to cutting-edge LLMs, autonomous multi-agent systems, and production RAG infrastructure.
Every guide across all 4 sub-curriculums adheres to the standardized two-tier learning structure:
- ⚡ Quick Dive: Architecture diagrams, mathematical formulas, algorithms matrices, and runnable Python/PyTorch one-liners.
- 📖 Extended Guide: Deep theoretical derivations, complete production code implementations, training pipelines, and architectural patterns.
🧭 Sub-Curriculum Directory
| Track Directory | Domain | Guides Count | Highlights & Core Topics | Track Master Link |
|---|---|---|---|---|
01_machine_learning_fundamentals/ |
ML Foundations & Statistics | 6 Guides | AI taxonomy for SEs, ML paradigms (supervised/unsupervised/RL), feature engineering pipelines, classical algorithms (XGBoost/LightGBM/K-Means), Bayesian probability, and evaluation metrics (ROC-AUC/F1). | 🧠 Open ML Foundations Index |
02_deep_learning_and_neural_architectures/ |
Deep Learning & Transformers | 8 Guides | Universal approximation, backpropagation & optimizers (AdamW), NLP foundations (BPE/Word2Vec), Computer Vision (CNNs/ResNet/ViT), Reinforcement Learning & RLHF, VAEs/Diffusion models, Transformer self-attention (FlashAttention/RoPE), and Multimodal models (CLIP/LLaVA). | 🔮 Open Deep Learning Index |
03_large_language_models_and_agents/ |
LLMs & Autonomous Agents | 6 Guides | Autoregressive LLM architectures & KV-caching, advanced prompt engineering (CoT/ToT), Parameter-Efficient Fine-Tuning (LoRA/QLoRA), ReAct autonomous agents, Multi-Agent systems (LangGraph), and LLM guardrails/safety. | 🤖 Open LLMs & Agents Index |
04_rag_and_vector_systems/ |
RAG & AI Infrastructure | 6 Guides | Dense vector embeddings, Vector Search (HNSW/IVF-PQ), RAG chunking & query transforms, Production RAG stack, GPU serving infrastructure (vLLM/PagedAttention), and Cross-Encoder rerankers (RRF/FlashRank). | 🔍 Open RAG & Vector Systems Index |