AI & Machine Learning

How AI systems work under the hood — from neural networks and transformers to RAG, agent patterns, and responsible deployment.

Neural Nets

Embeddings

Transformers

Tokenization

RAG

Fine-Tuning

AI Agents

Model Serving

Orchestration

Responsible AI

Foundations

Neural Networks Basics

Neurons, layers, activation functions, forward & backward propagation.

Embeddings & Vector Databases

Text → vectors, similarity search, Pinecone, Qdrant, and pgvector.

Transformer Architecture

Self-attention, positional encoding, and why LLMs work so well.

Tokenization & Context Windows

BPE, SentencePiece, token limits, and context management strategies.

Patterns & Training

RAG Architecture

Chunking, retrieval, prompt assembly, reranking, and evaluation.

Fine-Tuning vs Prompt Engineering

LoRA, QLoRA, few-shot, system prompts — when to use which.

AI Agents & Tool Use

ReAct pattern, function calling, agent loops, and multi-agent systems.

Deployment & Ethics

Model Serving & Inference

ONNX, quantization, batch inference, latency budgets, and GPU optimization.

LangChain / Semantic Kernel

Orchestration frameworks, chains, memory, and tool integration.

Responsible AI & Evaluation

Hallucination detection, bias, safety guardrails, and eval metrics.

Go deeper on these concepts

Want a specific AI or ML internal explained visually? Send a topic request and I will prioritize the concepts that are most useful for working engineers.

Suggest a topic

Cookie preferences

We use essential cookies for sign-in and preferences. With your permission, we also use basic analytics to improve lessons.