Can I learn machine learning with JavaScript?

Yes. Tensorcraft teaches machine learning entirely in JavaScript and TypeScript using TensorFlow JS (TensorFlow.js). Models train and run in the browser — no Python required. The curriculum covers neural networks, LSTMs, CNNs, and transformers through hands-on tutorials built for frontend developers.

How does Tensorcraft teach ML to frontend developers?

Tensorcraft uses 50+ 'bridge' analogies that map frontend concepts you already know (like useState, Array.map, and fetch) to their ML equivalents (model weights, tensor operations, and inference APIs). Each course is a story-driven narrative where you build real ML models.

Module 1 of every theme is free — no account or credit card required. Full themes cost $49 each, with bundle discounts available up to $129 for all 5 themes.

What ML topics does Tensorcraft cover?

Five specializations: Time-Series & Signals (RNNs, LSTMs), Computer Vision (CNNs, YOLO), NLP & Text Intelligence (Transformers, BERT), Multimodal & Generative AI (GANs, Diffusion), and Edge AI & Production ML (quantization, MLOps).

// COMPARE

Where each course wins.

Tensorcraft is not the right course for everyone. If you want paper-grade autograd internals, Karpathy's Zero-to-Hero is free and excellent. If you want hands-on PyTorch with Hugging Face superpowers, fast.ai is free and excellent. If you want a graded credential for your CV, Coursera does that and we don't.

Tensorcraft is the right course if you ship in the browser, you already know JavaScript, and you want a course that respects what you already know without watering down the ML. Every analogy ships with a label naming where it stops being literal — the bridge-tier system is woven directly into each lesson.

Course comparison: Tensorcraft vs fast.ai vs Karpathy zero-to-hero vs Coursera, scored across language, audience, math depth, deployment, capstone, cost, and credential.
Feature	Tensorcraft	fast.ai	Karpathy	Coursera
Primary language / runtime	JavaScript / TensorFlow.js (browser)	Python / PyTorch (Colab/local)	Python / PyTorch (notebooks)	Python / TensorFlow + Keras
Audience starting point	FE devs — useState, Array.reduce, Math.max	Anyone with Python comfort	Anyone willing to read math	Anyone with college calculus
Bridge-tier honesty	Identity / structural / intuition labels + breaks	Top-down practice; no formal tier system	Bottom-up math; no analogy framing	Formal definitions, less analogy
Math depth	Chain rule, softmax, KL, ELBO, DDPM derived	Pragmatic depth, not paper-grade	Paper-grade — autograd from scratch, attention from scratch	Theory + math, exam-grade
Browser-runtime + deployment	Every exercise grades in real TFJS in a worker	Cloud notebooks; deploy via paid fast.ai or third-party	Notebook only, no deployment story	Theory; deployment in separate specialization
Capstone artifact you ship	Five deployable browser-side ML apps	fast.ai notebooks shareable as Hugging Face Spaces	Final notebook trained from scratch	Certificates
Cost (full curriculum)	$0 preview / $129 all five themes	Free	Free	$49–79/mo (specialization $200–500)
Credential	None (your shipped artifact is the credential)	None	None	Coursera certificate

What we deliberately did not try to be

A Python ecosystem replacement. You will not learn pandas, PyTorch internals, or transformer fine-tuning here. fast.ai or Hugging Face NLP Course are better.
A research methodology course. We teach engineering practice, not how to design novel experiments. The Karpathy + d2l.ai combo is your friend.
A credential. Your capstone is a deployable browser-ML app you can show in an interview. That's the credential we believe in.

Start the course →Why this exists