1. Biological vs. Ar... 2. The McCulloch-Pit... 3. The XOR Problem a... 4. Universal Approxi... 5. Linear Algebra Fu... 6. Calculus & Matrix... 7. Activation Functi... 8. Modern Activation... 9. Advanced Activati... 10. Loss Functions f... 11. Loss Functions f... 12. Forward Propagat... 13. The Backpropagat... 14. Automatic Differ... 15. Vanishing and Ex... 16. Gradient Clippin... 17. Weight Initializ... 18. Weight Initializ... 19. Stochastic Gradi... 20. Momentum Optimiz... 21. Adaptive Optimiz... 22. The Adam Optimiz... 23. AdamW: Decoupled... 24. Learning Rate Sc... 25. L1 & L2 Regulari... 26. Dropout and Spat... 27. Early Stopping a... 28. Batch Normalizat... 29. Layer Normalizat... 30. GroupNorm, Insta... 31. 2D Convolutional... 32. Strides, Padding... 33. Pooling Layers: ... 34. Classic CNN Arch... 35. VGGNet: Small Fi... 36. GoogLeNet & Ince... 37. ResNet & Residua... 38. DenseNet: Featur... 39. MobileNets: Dept... 40. ConvNeXt & Moder... 41. Recurrent Neural... 42. Long Short-Term ... 43. Gated Recurrent ... 44. Bidirectional an... 45. Sequence-to-Sequ... 46. Bahdanau (Additi... 47. Scaled Dot-Produ... 48. Multi-Head Atten... 49. Positional Encod... 50. Relative & Rotar... 51. The Transformer ... 52. The Transformer ... 53. The Transformer ... 54. Vision Transform... 55. Swin Transformer... 56. Efficient Attent... 57. Multi-Query (MQA... 58. Mixture of Exper... 59. State Space Mode... 60. Tokenization Alg... 61. Classical Autoen... 62. Denoising and Sp... 63. Variational Auto... 64. The Reparameteri... 65. Vector Quantized... 66. Generative Adver... 67. Deep Convolution... 68. Wasserstein GAN ... 69. Conditional GANs... 70. Cycle-Consistent... 71. Diffusion Models... 72. Reverse Diffusio... 73. Accelerated Samp... 74. Latent Diffusion... 75. Classifier-Free ... 76. Contrastive Lear... 77. Non-Contrastive ... 78. Masked Autoencod... 79. Multimodal Visio... 80. Graph Neural Net... 81. Graph Convolutio... 82. Deep Q-Networks ... 83. Policy Gradient ... 84. Reinforcement Le... 85. Direct Preferenc... 86. Distributed Trai... 87. Model Parallelis... 88. Fully Sharded Da... 89. Mixed-Precision ... 90. Parameter-Effici... 91. Prefix Tuning, P... 92. Model Quantizati... 93. Advanced Weight ... 94. Network Pruning:... 95. Knowledge Distil... 96. Continual Learni... 97. Mechanistic Inte... 98. Adversarial Robu... 99. Inference Optimi... 100. Speculative Dec...