Skip to content
Instant download · PDF + web edition · Free sample of every book · 30-day refund promise
Latent Library Browse books
Deep Learning

Neural Networks From Scratch

Build, Train and Understand Every Piece

Pages
80
Chapters
42
Level
Intermediate
Format
E-book

About this book

Deep-learning libraries make it easy to train a network without understanding it. This book takes the opposite route: you build one from scratch, piece by piece, until nothing is mysterious.

You will implement neurons and layers, activation functions, loss functions, backpropagation and gradient descent, then improve training with better initialisation, momentum and adaptive optimisers, normalisation, dropout and early stopping. Short Python examples using only basic arrays accompany each step, alongside small calculations you can check by hand.

The final chapters connect your from-scratch network to the convolutional and transformer architectures used today.

What you will learn

  • How neurons, layers and activations compute
  • Loss functions for regression and classification
  • Backpropagation derived and computed step by step
  • Optimisers: momentum, RMSProp and Adam
  • Initialisation, normalisation, dropout and early stopping
  • How your network connects to modern architectures

Table of contents

  1. IntroductionIntroduction
  2. Chapter 1What a Neural Network Is
  3. Chapter 2A Single Neuron
  4. Chapter 3Activation Functions
  5. Chapter 4From Neurons to Layers
  6. Chapter 5The Forward Pass
  7. Chapter 6Output Layers
  8. Chapter 7Loss Functions for Regression
  9. Chapter 8Loss Functions for Classification
  10. Chapter 9Derivatives in One Page
  11. Chapter 10Gradients
  12. Chapter 11Backpropagation for One Neuron
  13. Chapter 12Backpropagation Through Layers
  14. Chapter 13Gradient Descent
  15. Chapter 14A Complete Network From Scratch
  16. Chapter 15Training and Test Data
  17. Chapter 16Initialisation
  18. Chapter 17Learning Rates
  19. Chapter 18Momentum
  20. Chapter 19Adaptive Optimisers: RMSProp and Adam
  21. Chapter 20Vanishing and Exploding Gradients
  22. Chapter 21Normalisation Layers
  23. Chapter 22Regularisation
  24. Chapter 23Dropout
  25. Chapter 24Early Stopping and Checkpoints
  26. Chapter 25Debugging Training
  27. Chapter 26From Dense Layers to Convolutions
  28. Chapter 27Sequences and Recurrent Networks
  29. Chapter 28Attention
  30. Chapter 29The Transformer
  31. Chapter 30A Two-Layer Backward Pass, by Hand
  32. Chapter 31A Multi-Class Training Loop
  33. Chapter 32Evaluating a Classifier
  34. Chapter 33Classifying Text With Embeddings
  35. Chapter 34Hyperparameter Search
  36. Chapter 35What Networks Learn
  37. Chapter 36Regression Networks in Practice
  38. Chapter 37Autoencoders
  39. Chapter 38Transfer Learning and Fine-Tuning
  40. Chapter 39Saving, Loading and Deploying a Model
  41. Chapter 40Using a Framework
  42. Chapter 41Practical Training Recipe
  43. Chapter 42Where to Go Next
  44. AppendixExercises
  45. GlossaryGlossary

Who this book is for

Developers and students with basic Python and algebra who want to understand deep learning from the ground up.

Details

FormatPDF + web edition
Length80 pages (approx.)
Chapters42
LevelIntermediate
LanguageEnglish
TopicDeep Learning
AuthorLatent Library Editorial

Keep reading

You may also like

All books
$12.99
Details