Buy once. Keep forever.

What’s in a Theme

every module in Deep Orbit, lesson by lesson

1. 01

   Module 1: Foundations: Tensors & Data

   Free

   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.

   5 lessons

   ~58 min
2. 02

   Module 2: Neural Networks: Layers & Architecture

   Build your first neural network from scratch. You'll learn how neurons, layers, and activations work, translating frontend component composition into network architecture.

   5 lessons

   ~79 min
3. 03

   Module 3: Training: Loss, Gradients & Optimization

   Train the DEEP SCAN signal classifier. You'll master loss functions, gradient descent, and the training loop: the engine that turns data into intelligence.

   5 lessons

   ~92 min
4. 04

   Module 4: Browser ML Runtimes

   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.

   6 lessons

   ~81 min
5. 05

   Module 5: Signal Processing

   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%.

   5 lessons

   ~72 min
6. 06

   Module 6: Recurrent Networks

   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.

   5 lessons

   ~68 min
7. 07

   Module 7: Anomaly Detection

   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.

   5 lessons

   ~71 min
8. 08

   Module 8: Advanced Time-Series

   The crew attempts to predict the anomalous signal's next occurrence. You'll build attention mechanisms, temporal convolutional networks, Kalman filters, and model ensembles: advanced forecasting tools that reveal the signal's timing is changing.

   5 lessons

   ~150 min
9. 09

   Module 9: LLM Integration

   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.

   5 lessons

   ~130 min
10. 10

    Module 10: Optimization & Edge

    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 only 2% accuracy loss, so it never happens again.

    5 lessons

    ~130 min
11. 11

    Module 11: Capstone: Deploy DEEP SCAN

    Deploy the complete DEEP SCAN signal classification system. System architecture, CI/CD pipeline, monitoring, documentation, and launch: everything the crew has built comes together.

    5 lessons

    ~130 min

Module 1 is free, no account needed. Browse the full Deep Orbit syllabus.