Introduction to Deep Learning: How about the Chinese version of Python-based theory and Implementation? Latest electronic PDF download:

This book is a true introduction to deep learning, which analyzes the principles and related technologies of deep learning in simple terms. Python3 is used in the book, and it does not rely on external libraries or tools as much as possible. Starting from basic mathematical knowledge, it leads readers to create a classic deep learning network from scratch, enabling readers to gradually understand deep learning in the process. The book not only introduces the deep learning of the neural network and the concept, features and other basic knowledge, the error back propagation method, convolution neural network also has a deep, moreover also introduced the deep learning relevant practical skills, autopilot, image generation and the application of reinforcement learning and so on, and why the deeper layer can improve the recognition accuracy, etc. The “why” question.

 

Catalogue

1 1.1 What is Python 1 1.2 Installing Python 2 1.3 The Python interpreter 4 1.4 Python script files 9 1.5 NumPy11 1.6 Matplotlib16 1.7 Summary 19 Chapter 2 Perceptron 21 2.1 What is a Perceptron 21 2.2 Simple Logic Circuit 23 2.3 Implementation of a Perceptron 25 2.4 Limitations of a Perceptron 28 2.5 Multilayer perceptron 31 2.6 From Nand Gates to Computers 35 2.7 Summary 36 Chapter 3 Neural Networks 37 3.2 Activation Functions 42 3.3 Operation of Multidimensional Arrays 50 3.43 Implementation of layer neural networks 56 3.5 Design of output layer 63 3.6 Handwritten digit recognition 69 3.7 Summary 79 Chapter 4 Learning of Neural networks 81 4.1 Learning from data 81 4.2 Loss function 85 4.3 Numerical differentiation 94 4.4 Gradient 100 4.5 Implementation of learning algorithms 109 4.6 Summary 118 Chapter 5 Error Backpropagation method 121 5.1 Calculation Figure 121 5.2 Chain rule 126 5.3 Backpropagation 130 5.4 Implementation of simple layer 135 5.5 Implementation of activation function layer 139 5.6 Implementation of AffineSoftmax layer 144 5.7 Implementation of the Error Back propagation method 154 5.8 Summary 161 Chapter 6 Learn-related Skills 163 6.1 Updating of parameters 163 6.2 Initial values of weights 176 6.4 Regularization 188 6.5 Verification of hyperparameters 195 6.6 Summary 200 Chapter 7 Convolutional Neural Network 201 7.1 Overall Structure 201 7.2 Convolutional layer 202 7.3 Pooling layer 214 7.4 Realization of convolutional layer and pooling layer 216 7.5 realization of CNN 224 7.6 VISUALIZATION of CNN 228 7.7 Representative CNN231 7.8 Summary 233 Chapter 8 Deep learning 235 8.1 Deepening the Network 235 8.2 A small history of Deep Learning 242 8.3 The High Speed of Deep Learning 248 8.5 The Future of Deep learning 258 8.6 Summary 264 Appendix Calculation figure of ASOFtMax-with-Loss layer 267 A.1 Forward propagation 268 A.2 Back propagation 270 A.3 Summary 277 Refs 279

 

Click on the download