Deep neural networks

This content introduces readers to the fundamentals of neural networks and deep neural networks, explaining their architecture and the processes of feed-forward and backward propagation for training. It guides users through coding practical deep learning models using the TF.Keras sequential and functional APIs, covering various model tasks like regression and classification. The material also delves into core concepts such as weights, biases, activations, and optimizers, and provides strategies to prevent common issues like overfitting, ensuring readers can build and optimize effective neural network solutions.

This page is free — overview and chapter list only.
The complete book body is sold separately.

Full book: $2.99 USDC via x402 ·
Per chapter: $0.25 USDC

Buy / open complete book (HTML)
· Complete book Markdown (.md)

Agents: start with free /library/discovery.json, sample free teaser chapters,
then pay for individual chapters or the complete book URL above.
Append .md to any content URL for Markdown with YAML front matter.

Chapters

  1. Deep Neural Networks (Free teaser)
  2. 21 Neural Network Basics ($0.25)
  3. 22 Dnn Binary Classifier ($0.25)
  4. 23 Dnn Multiclass Classifier ($0.25)
  5. 24 Dnn Multilabel Multiclass Classifier ($0.25)
  6. 25 Simple Image Classifier ($0.25)
  7. Summary ($0.25)
  8. 31 Convolutional Neural Networks ($0.25)
  9. 32 The Convnet Design For A Cnn ($0.25)
  10. 33 Vgg Networks ($0.25)
  11. 34 Resnet Networks ($0.25)
  12. Residual Block Resnet34 ($0.25)
  13. 41 Forward Feeding And Backward Propagation ($0.25)
  14. 42 Dataset Splitting ($0.25)
  15. 43 Data Normalization ($0.25)
  16. 44 Validation And Overfitting ($0.25)
  17. 45 Convergence ($0.25)
  18. 46 Checkpointing And Early Stopping ($0.25)
  19. 47 Hyperparameters ($0.25)
  20. 48 Invariance ($0.25)
  21. 49 Raw Disk Datasets ($0.25)
  22. Summary 2 ($0.25)
  23. 51 Basic Neural Network Architecture ($0.25)
  24. 52 Stem Component ($0.25)
  25. 53 Pre Stem ($0.25)
  26. 54 Learner Component ($0.25)
  27. 551 Resnet ($0.25)
  28. 561 Natural Language Understanding ($0.25)
  29. Summary 3 ($0.25)
  30. 611 Naive Inception Module ($0.25)
  31. 642 Resnext Architecture ($0.25)
  32. 651 Wrn 50 2 Architecture ($0.25)
  33. Summary 4 ($0.25)
  34. 81 Mobilenet V1 ($0.25)
  35. 852 Tf Lite Conversion And Prediction ($0.25)
  36. 911 Autoencoder Architecture ($0.25)
  37. 93 Sparse Autoencoders ($0.25)
  38. 951 Pre Upsampling Sr ($0.25)
  39. 96 Pretext Tasks ($0.25)
  40. 97 Beyond Computer Vision Sequence To Sequence ($0.25)
  41. This Chapter Covers ($0.25)
  42. 1011 Weight Distributions ($0.25)
  43. 1022 Grid Search ($0.25)
  44. 103 Learning Rate Scheduler ($0.25)
  45. 1032 Keras Learning Rate Scheduler ($0.25)
  46. 1034 Constant Step ($0.25)
  47. 104 Regularization ($0.25)
  48. 105 Beyond Computer Vision ($0.25)
  49. 111 Tfkeras Prebuilt Models ($0.25)
  50. 112 Tf Hub Prebuilt Models ($0.25)
  51. This Chapter Covers 2 ($0.25)
  52. 122 Out Of Distribution ($0.25)
  53. 1227 Final Test ($0.25)
  54. Drawing Batches From Compressed Images In Ram ($0.25)
  55. Hdf5 Groups ($0.25)
  56. Tfrecord Uncompressed Image ($0.25)
  57. Tfkeras Preprocessing Layers ($0.25)
  58. Chaining Pre Stems ($0.25)
  59. Tfkeras Subclassing Layers ($0.25)
  60. Schemagen ($0.25)
  61. Transform ($0.25)
  62. 1342 Augmentation With Tfdata ($0.25)
  63. 1343 Pre Stem ($0.25)
  64. This Chapter Covers 3 ($0.25)
  65. Model Feeder For Sequential Training ($0.25)
  66. 1411 Model Feeding With Tfdatadataset ($0.25)
  67. Dynamically Updating The Batch Size ($0.25)
  68. 1412 Distributed Feeding With Tfstrategy ($0.25)
  69. Orchestration ($0.25)
  70. Trainer Component ($0.25)
  71. Tuner Component ($0.25)
  72. 1421 Pipeline Versioning ($0.25)
  73. 1422 Metadata ($0.25)
  74. 1423 History ($0.25)
  75. Serving Skew ($0.25)
  76. 1441 On Demand Live Serving ($0.25)
  77. 1443 Tfx Pipeline Components For Deployment ($0.25)
  78. 1445 Load Balancing ($0.25)
  79. 1446 Continuous Evaluation ($0.25)
  80. Summary 5 ($0.25)