万本电子书0元读

万本电子书0元读

顶部广告

Neural Networks with Keras Cookbook电子书

售       价:¥

1人正在读 | 0人评论 9.8

作       者:V Kishore Ayyadevara

出  版  社:Packt Publishing

出版时间:2019-02-28

字       数:55.3万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:数字商品不支持退换货,不提供源文件,不支持导出打印

为你推荐

  • 读书简介
  • 目录
  • 累计评论(0条)
  • 读书简介
  • 目录
  • 累计评论(0条)
Implement neural network architectures by building them from scratch for multiple real-world applications. Key Features * From scratch, build multiple neural network architectures such as CNN, RNN, LSTM in Keras * Discover tips and tricks for designing a robust neural network to solve real-world problems * Graduate from understanding the working details of neural networks and master the art of fine-tuning them Book Description This book will take you from the basics of neural networks to advanced implementations of architectures using a recipe-based approach. We will learn about how neural networks work and the impact of various hyper parameters on a network's accuracy along with leveraging neural networks for structured and unstructured data. Later, we will learn how to classify and detect objects in images. We will also learn to use transfer learning for multiple applications, including a self-driving car using Convolutional Neural Networks. We will generate images while leveraging GANs and also by performing image encoding. Additionally, we will perform text analysis using word vector based techniques. Later, we will use Recurrent Neural Networks and LSTM to implement chatbot and Machine Translation systems. Finally, you will learn about transcribing images, audio, and generating captions and also use Deep Q-learning to build an agent that plays Space Invaders game. By the end of this book, you will have developed the skills to choose and customize multiple neural network architectures for various deep learning problems you might encounter. What you will learn * Build multiple advanced neural network architectures from scratch * Explore transfer learning to perform object detection and classification * Build self-driving car applications using instance and semantic segmentation * Understand data encoding for image, text and recommender systems * Implement text analysis using sequence-to-sequence learning * Leverage a combination of CNN and RNN to perform end-to-end learning * Build agents to play games using deep Q-learning Who this book is for This intermediate-level book targets beginners and intermediate-level machine learning practitioners and data scientists who have just started their journey with neural networks. This book is for those who are looking for resources to help them navigate through the various neural network architectures; you'll build multiple architectures, with concomitant case studies ordered by the complexity of the problem. A basic understanding of Python programming and a familiarity with basic machine learning are all you need to get started with this book.
目录展开

Title Page

Copyright and Credits

Neural Networks with Keras Cookbook

Dedication

About Packt

Why subscribe?

Packt.com

Contributors

About the author

About the reviewer

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

Sections

Getting ready

How to do it…

How it works…

There's more…

See also

Get in touch

Reviews

Building a Feedforward Neural Network

Introduction

Architecture of a simple neural network

Training a neural network

Applications of a neural network

Feed-forward propagation from scratch in Python

Getting ready

How to do it...

Building back-propagation from scratch in Python

Getting ready

How to do it...

There's more...

Building a neural network in Keras

How to do it...

Installing Keras

Building our first model in Keras

Building a Deep Feedforward Neural Network

Training a vanilla neural network

Getting ready

How to do it...

How it works...

Scaling the input dataset

Getting ready

How to do it...

How it works...

There's more...

Impact on training when the majority of inputs are greater than zero

Getting ready

How to do it...

Impact of batch size on model accuracy

Getting ready

How to do it...

How it works...

Building a deep neural network to improve network accuracy

Getting ready

How to do it...

Varying the learning rate to improve network accuracy

Getting ready

How to do it...

Varying the loss optimizer to improve network accuracy

Getting ready

There's more...

Understanding the scenario of overfitting

Overcoming over-fitting using regularization

How to do it

Overcoming overfitting using dropout

Speeding up the training process using batch normalization

How to do it...

Applications of Deep Feedforward Neural Networks

Introduction

Predicting credit default

Getting ready

How to do it...

How it works...

Assigning weights for classes

Getting ready

How to do it...

Predicting house prices

Getting ready

How to do it...

Defining the custom loss function

Categorizing news articles into topics

Getting ready

How to do it...

Classifying common audio

How to do it...

Stock price prediction

Getting ready

How to do it...

Leveraging a functional API

How to do it...

Defining weights for rows

How to do it...

Building a Deep Convolutional Neural Network

Introduction

Inaccuracy of traditional neural networks when images are translated

How to do it...

Problems with traditional NN

Building a CNN from scratch using Python

Getting ready

Understanding convolution

Filter

Strides

Padding

From convolution to activation

From convolution activation to pooling

How do convolution and pooling help?

How to do it...

Validating the CNN output

CNNs to improve accuracy in the case of image translation

Getting ready

How to do it...

Gender classification using CNNs

Getting ready

How to do it...

There's more...

Data augmentation to improve network accuracy

Getting ready

How to do it...

Model accuracy without data augmentation

Model accuracy with data augmentation

Transfer Learning

Gender classification of the person in an image using CNNs

Getting ready

How to do it...

Scenario 1 – big images

Scenario 2 – smaller images

Scenario 3 – aggressive pooling on big images

Gender classification of the person in image using the VGG16 architecture-based model

Getting ready

How to do it...

Visualizing the output of the intermediate layers of a neural network

Getting ready

How to do it...

Gender classification of the person in image using the VGG19 architecture-based model

Getting ready

How to do it...

Gender classification using the Inception v3 architecture-based model

How to do it...

Gender classification of the person in image using the ResNet 50 architecture-based model

How to do it...

Detecting the key points within image of a face

Getting ready

How to do it...

Detecting and Localizing Objects in Images

Introduction

Creating the dataset for a bounding box

How to do it...

Windows

Ubuntu

MacOS

Generating region proposals within an image, using selective search

Getting ready

How to do it...

Calculating an intersection over a union between two images

How to do it...

Detecting objects, using region proposal-based CNN

Getting ready

How to do it...

Performing non-max suppression

Getting ready

How to do it...

Detecting a person using an anchor box-based algorithm

Getting ready

How to do it...

There's more...

Image Analysis Applications in Self-Driving Cars

Traffic sign identification

Getting ready

How to do it...

Predicting the angle within which a car needs to be turned

Getting ready

How to do it...

Instance segmentation using the U-net architecture

Getting ready

How to do it...

Semantic segmentation of objects in an image

Getting ready

How to do it...

Image Generation

Introduction

Generating images that can fool a neural network using adversarial attack

Getting ready

How to do it...

DeepDream algorithm to generate images

Getting ready

How to do it...

Neural style transfer between images

Getting ready

How to do it...

Generating images of digits using Generative Adversarial Networks

Getting ready

How to do it...

There's more...

Generating images using a Deep Convolutional GAN

How to do it...

Face generation using a Deep Convolutional GAN

Getting ready

How to do it...

Face transition from one to another

Getting ready

How to do it...

Performing vector arithmetic on generated images

Getting ready

How to do it...

There's more...

Encoding Inputs

Introduction

Need for encoding

Need for encoding in text analysis

Need for encoding in image analysis

Need for encoding in recommender systems

Encoding an image

Getting ready

How to do it...

Vanilla autoencoder

Multilayer autoencoder

Convolutional autoencoder

Grouping similar images

Encoding for recommender systems

Getting ready

How to do it...

Text Analysis Using Word Vectors

Introduction

Building a word vector from scratch in Python

Getting ready

How to do it...

Measuring the similarity between word vectors

Building a word vector using the skip-gram and CBOW models

Getting ready

How to do it

Performing vector arithmetic using pre-trained word vectors

How to do it...

Creating a document vector

Getting ready

How to do it...

Building word vectors using fastText

Getting ready

How to do it...

Building word vectors using GloVe

Getting ready

How to do it...

Building sentiment classification using word vectors

How to do it...

There's more...

Building a Recurrent Neural Network

Introduction

Intuition of RNN architecture

Interpreting an RNN

Why store memory?

Building an RNN from scratch in Python

Getting ready

How to do it...

Validating the output

Implementing RNN for sentiment classification

How to do it...

There's more...

Building a LSTM Network from scratch in Python

Getting ready

How to do it...

Validating the output

Implementing LSTM for sentiment classification

How to do it...

Implementing stacked LSTM for sentiment classification

How to do it...

There's more...

Applications of a Many-to-One Architecture RNN

Generating text

Getting ready

How to do it...

Movie recommendations

Getting ready

How to do it...

Taking user history into consideration

Topic-modeling, using embeddings

Getting ready

How to do it...

There's more...

Forecasting the value of a stock's price

Getting ready

How to do it...

The last five days' stock prices only

The pitfalls

Assigning different weights to different time periods

The last five days' stock prices plus news data

There's more...

Sequence-to-Sequence Learning

Introduction

Returning sequences of outputs from a network

Building a chatbot

Getting ready

How to do it...

Intent extraction

Putting it all together

Machine translation

Getting ready

How to do it...

Preprocessing the data

Traditional many to many architecture

Many to hidden to many architecture

Encoder decoder architecture for machine translation

Getting ready

How to do it...

Encoder decoder architecture with attention for machine translation

How to do it...

End-to-End Learning

Introduction

Connectionist temporal classification (CTC)

Decoding CTC

Calculating the CTC loss value

Handwritten-text recognition

Getting ready

How to do it...

Image caption generation

Getting ready

How to do it...

Generating captions, using beam search

Getting ready

How to do it...

Audio Analysis

Classifying a song by genre

Getting ready

How to do it...

Generating music using deep learning

Getting ready

How to do it...

Transcribing audio into text

Getting ready

How to do it...

There's more...

Reinforcement Learning

The optimal action to take in a simulated game with a non-negative reward

Getting ready

How to do it...

The optimal action to take in a state in a simulated game

Getting ready

How to do it...

There's more...

Q-learning to maximize rewards when playing Frozen Lake

Getting ready

How to do it...

Deep Q-learning to balance a cart pole

Getting ready

How to do it...

Deep Q-learning to play Space Invaders game

Getting ready

How to do it...

Other Books You May Enjoy

Leave a review - let other readers know what you think

累计评论(0条) 0个书友正在讨论这本书 发表评论

发表评论

发表评论,分享你的想法吧!

买过这本书的人还买过

读了这本书的人还在读

回顶部