Thomas Piacentini
← Workshop

Book

2. Deep Learning

Original text · English

Networks, Vision, and Speech

  1. The Perceptron: Where It All Started
  2. Multi-Layer Networks & Forward Pass
  3. Backpropagation from Scratch
  4. Activation Functions: ReLU, Sigmoid, GELU & Why
  5. Loss Functions: MSE, Cross-Entropy, Contrastive
  6. Optimizers: SGD, Momentum, Adam, AdamW
  7. Regularization: Dropout, Weight Decay, BatchNorm
  8. Weight Initialization & Training Stability
  9. Learning Rate Schedules & Warmup
  10. Build Your Own Mini Framework
  11. Introduction to PyTorch
  12. Introduction to JAX
  13. Debugging Neural Networks
  14. Image Fundamentals: Pixels, Channels, Color Spaces
  15. Convolutions from Scratch
  16. CNNs: LeNet to ResNet
  17. Image Classification
  18. Transfer Learning & Fine-Tuning
  19. Object Detection — YOLO from Scratch
  20. Semantic Segmentation — U-Net
  21. Instance Segmentation — Mask R-CNN
  22. Image Generation — GANs
  23. Image Generation — Diffusion Models
  24. Stable Diffusion — Architecture & Fine-Tuning
  25. Video Understanding — Temporal Modeling
  26. 3D Vision: Point Clouds, NeRFs
  27. Vision Transformers (ViT)
  28. Real-Time Vision: Edge Deployment
  29. Build a Complete Vision Pipeline
  30. Self-Supervised Vision — SimCLR, DINO, MAE
  31. Open-Vocabulary Vision — CLIP
  32. OCR & Document Understanding
  33. Image Retrieval & Metric Learning
  34. Keypoint Detection & Pose Estimation
  35. 3D Gaussian Splatting from Scratch
  36. Diffusion Transformers & Rectified Flow
  37. SAM 3 & Open-Vocabulary Segmentation
  38. Vision-Language Models (ViT-MLP-LLM)
  39. Monocular Depth & Geometry Estimation
  40. Multi-Object Tracking & Video Memory
  41. World Models & Video Diffusion
  42. Audio Fundamentals: Waveforms, Sampling, FFT
  43. Spectrograms, Mel Scale & Audio Features
  44. Audio Classification
  45. Speech Recognition (ASR)
  46. Whisper: Architecture & Fine-Tuning
  47. Speaker Recognition & Verification
  48. Text-to-Speech (TTS)
  49. Voice Cloning & Voice Conversion
  50. Music Generation
  51. Audio-Language Models
  52. Real-Time Audio Processing
  53. Build a Voice Assistant Pipeline
  54. Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC
  55. Voice Activity Detection & Turn-Taking
  56. Streaming Speech-to-Speech — Moshi, Hibiki
  57. Voice Anti-Spoofing & Audio Watermarking
  58. Audio Evaluation — WER, MOS, MMAU, Leaderboards
Complete volume source (Markdown) ↓Printable HTML volume ↗
Code and artifacts 1
What you take away

Saved in your notebook on this device.

Sources and limits

Reading checkpoints are self-reported. Test results are recorded separately and apply to the executed cases.

AI Engineering from Scratch · 3f9715c · MIT

Download this file ↓