🧠TensorToIntelligence¶
Welcome to TensorToIntelligence — a build-in-public deep learning education series.
What You'll Learn¶
Each module in this series covers a first-principles implementation of a deep learning primitive:
- Phase 1: Primitives — Linear layers, activations, loss functions, optimizers
- Phase 2: Architectures — CNNs, ResNets, RNNs, LSTMs
- Phase 3: Transformers — Attention, BERT, GPT, KV-cache
- Phase 4: Generative — VAE, GAN, Diffusion models
- Phase 5: Frontier — SSMs, MoE, LoRA, Quantization
Philosophy¶
Every module follows the same structure:
- Intuition — Why does this exist?
- Math — Formal derivation with LaTeX
- Code — Annotated Python implementation
- Test — Proof of parity with
torch.nn - Experiment — Visualizations and insights
Getting Started¶
Check out the Roadmap to see the full learning path, then dive into Phase 1 to begin your journey!