Each theme is a separate ML specialization. Buy the one that fits, one payment, lifetime access, no subscription.
14-day money-back guarantee: full refund within 14 days, no questions asked. Email support@tensorcraft.app. See terms.
bundle pricing · 1 of 5 themes built
Bundle pricing exists for when more themes do. Deep Orbit is the one theme built today, and at $59 it is the only thing on this page you can buy. The rest unlock as themes ship, and we are not putting a date on that.
every module in Deep Orbit, lesson by lesson
Board the Archimedes and learn to see data the way neural networks do. You'll master tensors, shapes, and operations (the building blocks of every ML model) using concepts you already know from frontend development.
Build your first neural network from scratch. You'll learn how neurons, layers, and activations work, translating frontend component composition into network architecture.
Train the DEEP SCAN signal classifier. You'll master loss functions, gradient descent, and the training loop: the engine that turns data into intelligence.
Take your trained model out of the lab and into the browser. Nazari challenges Demir to deploy the DEEP SCAN classifier on the ship's browser-based dashboard, with real performance constraints. You'll master TensorFlow.js setup, model loading, real-time inference, and compare runtimes like a frontend engineer compares frameworks.
Dr. Farah discovers hidden structure in the signals that only appears in the frequency domain. You'll master the Fourier Transform, spectrograms, and windowing, transforming raw time-series data into rich features that boost DEEP SCAN's accuracy from 78% to 87%.
The signals show temporal patterns: a rhythm spanning dozens of time steps. Feedforward networks see snapshots; recurrent networks see sequences. You'll build RNNs, LSTMs, and GRUs that remember past inputs and predict what comes next, using concepts from Redux reducers and localStorage caching.
DEEP SCAN's anomaly detector fires on a signal that matches no known category. The reconstruction error is off the charts. You'll build autoencoders that learn what "normal" looks like, then flag anything that deviates, using the same intuition as git diff and error boundaries.
The crew attempts to predict the anomalous signal's next occurrence. You'll build attention mechanisms, multi-step forecasts, Kalman filters, and confidence-weighted ensembles: advanced tools that reveal the signal's timing is changing.
Mirza needs a comprehensive report for Earth Command: 47 days of data, 12,000 classified signals, and one anomaly that could change everything. You'll integrate language models into DEEP SCAN: prompt engineering, RAG over signal logs, and multi-model orchestration.
Nazari's module, and a penance. At 0247 the 340 MB model crashed the 512 MB bridge dashboard during a predicted pulse window; the capture was lost and Earth's relay slot closed without it. You'll master quantization, pruning, caching, and WebGPU acceleration to shrink the model to 42 MB with 2.4% accuracy loss, measured and refused rounding, so it never happens again.
Deploy the complete DEEP SCAN signal classification system. System architecture, CI/CD pipeline, monitoring, documentation, and launch: everything the crew has built comes together.
Module 1 is free, no account needed. Browse the full Deep Orbit syllabus.
Yes. Tensorcraft teaches machine learning entirely in JavaScript and TypeScript using TensorFlow.js. Models train and run in the browser, no Python required. The launched theme covers neural networks, LSTMs, signal processing, and attention today; CNNs and full transformer architectures arrive with the Computer Vision and NLP themes now in development.
Through 55 '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.
None upfront. You need working JavaScript: comfortable with functions, arrays, and async. The math is there when you want it: derivations sit in optional expandable drawers, and you can finish every module without opening one.
Module 1 of Deep Orbit, the live theme, is free, no account or credit card required. The other four themes ship in waves, each with a waitlist. Full themes cost $59 each; bundle discounts, up to $159 for all 5 themes, open once all five have launched.
Five specializations, one live today and four in development: Time-Series & Signals (RNNs, LSTMs, live now), Computer Vision (CNNs, YOLO), NLP & Text Intelligence (Transformers, BERT), Multimodal & Generative AI (GANs, Diffusion), and Edge AI & Production ML (quantization, MLOps).
Module 1 is free before any money moves. After purchase there's a 14-day money-back guarantee: full refund, no questions asked. Email support@tensorcraft.app.
your frontend is the foundation
Start with the free preview. Upgrade when you’re ready.
See All 5 Themes →