Hands-On Neural Networks电子书

Dedication

About Packt

Why subscribe?

Packt.com

Contributors

About the authors

About the reviewers

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Section 1: Getting Started

Getting Started with Supervised Learning

History of AI

An overview of machine learning

Supervised learning

Unsupervised learning

Semi-supervised learning

Reinforcement learning

Environment setup

Understanding virtual environments

Anaconda

Docker

Supervised learning in practice with Python

Data cleaning

Feature engineering

How deep learning performs feature engineering

Feature scaling

Feature engineering in Keras

Supervised learning algorithms

Metrics

Regression metrics

Classification metrics

Evaluating the model

TensorBoard

Summary

Neural Network Fundamentals

The perceptron

Implementing a perceptron

Keras

Implementing perceptron in Keras

Feedforward neural networks

Introducing backpropagation

Activation functions

Sigmoid

Softmax

Tanh

ReLU

Keras implementation

The chain rule

The XOR problem

FFNN in Python from scratch

FFNN Keras implementation

TensorBoard

TensorBoard on the XOR problem

Summary

Section 2: Deep Learning Applications

Convolutional Neural Networks for Image Processing

Understanding CNNs

Input data

Convolutional layers

Pooling layers

Stride

Max pooling

Zero padding

Dropout layers

Normalization layers

Output layers

CNNs in Keras

Loading the data

Creating the model

Network configuration

Keras for expression recognition

Optimizing the network

Summary

Exploiting Text Embedding

Machine learning for NLP

Rule-based methods

Understanding word embeddings

Applications of words embeddings

Word2vec

Word embedding in Keras

Pre-trained network

GloVe

Global matrix factorization

Using the GloVe model

Text classification with GloVe

Summary

Working with RNNs

Understanding RNNs

Theory behind CNNs

Types of RNNs

One-to-one

One-to-many

Many-to-many

The same lag

A different lag

Loss functions

Long Short-Term Memory

LSTM architecture

LSTMs in Keras

PyTorch basics

Time series prediction

Summary

Reusing Neural Networks with Transfer Learning

Transfer learning theory

Introducing multi-task learning

Reusing other networks as feature extractors

Implementing MTL

Feature extraction

Implementing TL in PyTorch

Summary

Section 3: Advanced Applications

Working with Generative Algorithms

Discriminative versus generative algorithms

Understanding GANs

Training GANs

GAN challenges

GAN variations and timelines

Conditional GANs

DCGAN

ReLU versus Leaky ReLU

DCGAN – a coded example

Pix2Pix GAN

StackGAN

CycleGAN

ProGAN

StarGAN

StarGAN discriminator objectives

StarGAN generator functions

BigGAN

StyleGAN

Style modules

StyleGAN implementation

Deepfakes

RadialGAN

Summary

Further reading

Implementing Autoencoders

Overview of autoencoders

Autoencoder applications

Bottleneck and loss functions

Standard types of autoencoder

Undercomplete autoencoders

Example

Visualizing with TensorBoard

Visualizing reconstructed images

Multilayer autoencoders

Example

Convolutional autoencoders

Example

Sparse autoencoders

Example

Denoising autoencoders

Example

Contractive autoencoder

Variational Autoencoders

Training VAEs

Example

Summary

Further reading

Deep Belief Networks

Overview of DBNs

BBNs

Predictive propagation

Retrospective propagation

RBMs

RBM training

Example – RBM recommender system

Example – RBM recommender system using code

DBN architecture

Training DBNs

Fine-tuning

Datasets and libraries

Example – supervised DBN classification

Example – supervised DBN regression

Example – unsupervised DBN classification

Summary

Further reading

Reinforcement Learning

Basic definitions

Introducing Q-learning

Learning objectives

Policy optimization

Methods of Q-learning

Playing with OpenAI Gym

The frozen lake problem

Summary

Whats Next?

Summarizing the book

Future of machine learning

Artificial general intelligence

Ethics in AI

Interpretability

Automation

AI safety

AI ethics

Accountability

Conclusions

Other Books You May Enjoy

Leave a review - let other readers know what you think