← All free books
Cover of The Why Book of Deep Learning

free to read · 752 pages

The Why Book of Deep LearningPart 1

by Dr. Philemon Paul Daniel

Why every piece of a neural network is there, with Keras notebooks for every lesson and almost no maths. Written for engineering students and working professionals, as the grown-up sequel to the AI Kids Guru deep-learning video course.

Chapters

Click a chapter to open it as a book you can flip through. The chips under a chapter open its notebooks in Google Colab, free, with nothing to install.

  1. ·Cover, how to use this book, contents5 pages
  2. Part I · The Learning Machine
  3. 1What Learning Really Ispp. 3–24
  4. 2Tensors and Shapes: The Grammar of Deep Learningpp. 25–44
  5. 3One Neuronpp. 45–64
  6. 4Stacking Neurons: Dense Layers and the MLPpp. 65–84
  7. Part II · Making It Learn
  8. 5Activation Functions: Every One, and Whenpp. 87–118
  9. 6Loss Functions: Every One, and Whenpp. 119–152
  10. 7Backpropagation by Handpp. 153–174
  11. 8Optimizers and the Learning Ratepp. 175–198
  12. 9Vanishing and Exploding Gradientspp. 199–220
  13. 10Normalization Layerspp. 221–240
  14. 11Overfitting and Regularizationpp. 241–262
  15. 12The Training Cockpit: Curves, Metrics and Debuggingpp. 263–286
  16. Part III · Seeing
  17. 13Convolution: One Small Windowpp. 289–308
  18. 14Shapes, Channels and Parameterspp. 309–324
  19. 15The Conv Toolbox: Pooling, Stride, Receptive Field and Friendspp. 325–346
  20. 16Building Real CNNs: Fashion-MNIST and CIFAR-10pp. 347–370
  21. 17Famous Architectures and the Skip Connectionpp. 371–392
  22. Part IV · Meaning and Memory
  23. 18Embeddings: Turning Things into Vectorspp. 395–420
  24. 19Recurrent Networkspp. 421–444
  25. 20LSTM and GRUpp. 445–466
  26. 21Sequence to Sequence and the Bottleneckpp. 467–488
    Run it:Lab10_LSTM
  27. Part V · Attending
  28. 22Attentionpp. 491–512
  29. 23The Transformer Blockpp. 513–534
  30. 24Feed-Forward (MLP) Layers: The Quiet Half of Every Modelpp. 535–554
  31. 25Linear Attention and Other Ways to Beat n²pp. 555–576
  32. 26State-Space Models: From Kalman to Mambapp. 577–598
  33. Part VI · Imagining
  34. 27Autoencoderspp. 601–620
  35. 28Variational Autoencoderspp. 621–642
  36. 29The Generative Family: GANs, Diffusion and Friendspp. 643–666
  37. Part VII · The Craft
  38. 30The Keras Field Guidepp. 669–696
  39. 31Choosing an Architecturepp. 697–720
  40. 32The Big Cheat Sheetspp. 721–747

The notebooks

Every lesson that can be run has a Keras notebook: checked, run from top to bottom and saved with its outputs, so you can read the results before you run anything. They live in github.com/phildani7/why-book-of-deep-learning-part-1, each named after its main chapter. Tested with TensorFlow 2.21 and Keras 3.14.

Ch.NotebookRunSource
1ch01_LabCh01_What_Learning_Is.ipynbOpen in ColabGitHub
3ch03_Lab01_2026_stepwise.ipynbOpen in ColabGitHub
4ch04_KidsLab02_MNIST_Digit_Recognition.ipynbOpen in ColabGitHub
4ch04_Lab02_2026_MNIST_10Digit_Interactive.ipynbOpen in ColabGitHub
5ch05_Lab05_2026_Activation_Functions_with_outputs.ipynbOpen in ColabGitHub
6ch06_Lab07_Loss_Functions_with_outputs.ipynbOpen in ColabGitHub
7ch07_Lab03_2026_Backpropagation_ChainRule_ByHand.ipynbOpen in ColabGitHub
8ch08_LabCh08_Optimizers_And_Learning_Rate.ipynbOpen in ColabGitHub
10ch10_LabCh10_Normalization_Layers.ipynbOpen in ColabGitHub
13ch13_KidsLab03_Edge_Detection_Kernels.ipynbOpen in ColabGitHub
13ch13_Lab04_2026_CNN_MNIST_stepwise.ipynbOpen in ColabGitHub
16ch16_KidsLab04_Fashion_MNIST_CNN.ipynbOpen in ColabGitHub
16ch16_KidsLab05_CIFAR10_CNN.ipynbOpen in ColabGitHub
16ch16_KidsLab05_CIFAR10_Layer_Visualization.ipynbOpen in ColabGitHub
17ch17_LabCh17_Residual_Blocks_And_Transfer_Learning.ipynbOpen in ColabGitHub
18ch18_KidsLab06_Word_Magic_Equations.ipynbOpen in ColabGitHub
19ch19_Lab08_RNN_Number_Prediction.ipynbOpen in ColabGitHub
20ch20_KidsLab07_LSTM_Sequence_Predictor.ipynbOpen in ColabGitHub
20ch20_KidsLab08_LSTM_Project.ipynbOpen in ColabGitHub
20ch20_Lab10_LSTM.ipynbOpen in ColabGitHub
22ch22_LabCh22_Attention_By_Hand.ipynbOpen in ColabGitHub
23ch23_LabCh23_Transformer_Block.ipynbOpen in ColabGitHub
24ch24_LabCh24_FeedForward_Layers.ipynbOpen in ColabGitHub
25ch25_LabCh25_Linear_Attention.ipynbOpen in ColabGitHub
26ch26_LabCh26_State_Space_Models.ipynbOpen in ColabGitHub
27ch27_LabCh27_Autoencoders.ipynbOpen in ColabGitHub
28ch28_LabCh28_Variational_Autoencoder.ipynbOpen in ColabGitHub
29ch29_LabCh29_Generative_Models.ipynbOpen in ColabGitHub

Reviews

What readers think of the book. Every rating counts in the average; names are shown only when a reader gives one.

Loading the reviews…