Track 1 · Beginner · 19 modules
How Do Machines Learn?
What AI is, how it differs from ordinary software, what a neuron does, and how a network learns from its mistakes.
Interactive courses in plain language. Race a CPU against a GPU, watch attention pick the words that matter, and train a network of your own. No math background needed. Every idea has something to play with.
Nine tracks, in order. Each one builds on the last.
Track 1 · Beginner · 19 modules
What AI is, how it differs from ordinary software, what a neuron does, and how a network learns from its mistakes.
Track 2 · Beginner → Intermediate · 21 modules
How a chatbot works inside: tokens, meaning, attention and the transformer, how models are trained and scaled, and why they hallucinate.
Track 3 · Intermediate · 12 modules
Why AI needs so much simple arithmetic, how GPUs and tensor cores do it in parallel, why moving data is the real bottleneck, and what it takes to run and train a model.
Track 4 · Advanced · 13 modules
What happens after you press send: prefill and decode, batching, the KV cache, splitting models over GPUs, serving engines, and what each answer costs.
Track 5 · Intermediate · 13 modules
How apps talk to models through APIs, how to choose a model, how to write prompts and system prompts, and how to get structured, streamed and affordable answers.
Track 6 · Intermediate → Advanced · 11 modules
Why models don’t know your facts, how meaning search and vector databases find them, how RAG feeds them to the model, and when fine-tuning is the better tool.
Track 7 · Intermediate → Advanced · 13 modules
How a model uses tools, works in a loop of thinking and acting, remembers, connects through MCP, works in teams, and stays under your control.
Track 8 · Intermediate · 10 modules
How models understand and create images, speech and video, not only text.
Track 9 · Advanced · 6 modules
How to judge an answer, where bias and leaks come from, how models get tricked, and whether we can see inside them.
A hands-on workshop. Warm up here, or come back any time you want to train a network yourself.