Why this course exists.

Most ML courses teach you ML. Tensorcraft teaches you ML by mapping it to the frontend code you already write: useState becomes model parameters, Array.reduce becomes a neuron, Math.max(0, x) literally is ReLU. The bridges aren't marketing. They're the curriculum.

Every analogy ships with a label that names where it stops being literal. We call this the bridge-tier system: identity (literally the same), structural (same shape, different domain), intuition (same mental model, different math). Structural and intuition bridges include a note on where the analogy ends so you stop carrying the wrong model into production.

Every exercise grades against real TensorFlow.js, not a mock. 80 exercises live today at 100% solution-passes-all-tests, all running in a worker in your browser, with 315 authored across the five-theme roadmap and held to the same bar. If a test fails, the model behavior is actually wrong; not a string-match heuristic.

Five themes (Deep Orbit, Neon Protocol, Signal Ward, Nova Canvas, Terra Grid) wrap the curriculum in narrative. Each one builds toward a working browser-side ML system, assembled piece by piece across the modules; connect GitHub and every solved exercise pushes to your repo. The story keeps you on the page; understanding every layer of what you built is what you take to interviews.

What we deliberately left out

• Python ecosystem coverage. If you want PyTorch / Hugging Face / pandas mastery, fast.ai and the Hugging Face NLP Course are excellent and free.
• GPU training pipelines. Browser ML lives within the inference budget the user's device gives you. Distributed GPU training is a different sport.
• Paper-grade math derivations. Chain rule, softmax, KL, cross-entropy. All derived. Beyond that, Karpathy's Zero-to-Hero is the right course.
• Research methodology. We teach engineering practice, not novel research design.

The audit trail

We publish our own audits. The blog includes the bridge-tier audit (every lesson, classified), the fast.ai comparison (where they win, where we win), and the exercise mlContent audit (what each exercise actually exercises vs. what its badge claims). If you find something we got wrong, the source is on GitHub.

Built by FE devs who shipped ML

Tensorcraft is authored by frontend engineers who shipped ML in production web apps before writing the curriculum. We built the course we wanted when we started. Every analogy was tested against our own missed-it-the-first-time mistakes.