Keras 2.x Projects

图书信息

作者	Giuseppe Ciaburro
出版社	Packt Publishing
ISBN	9781789534160
出版时间	2018-12-31
字数	51.1万
分类	进口书,外文原版书,电脑,网络

读书简介

Demonstrate fundamentals of Deep Learning and neural network methodologies using Keras 2.x Key Features *Experimental projects showcasing the implementation of high-performance deep learning models with Keras. * *Use-cases across reinforcement learning, natural language processing, GANs and computer vision. * *Build strong fundamentals of Keras in the area of deep learning and artificial intelligence. Book Description Keras 2.x Projects explains how to leverage the power of Keras to build and train state-of-the-art deep learning models through a series of practical projects that look at a range of real-world application areas. To begin with, you will quickly set up a deep learning environment by installing the Keras library. Through each of the projects, you will explore and learn the advanced concepts of deep learning and will learn how to compute and run your deep learning models using the advanced offerings of Keras. You will train fully-connected multilayer networks, convolutional neural networks, recurrent neural networks, autoencoders and generative adversarial networks using real-world training datasets. The projects you will undertake are all based on real-world scenarios of all complexity levels, covering topics such as language recognition, stock volatility, energy consumption prediction, faster object classification for self-driving vehicles, and more. By the end of this book, you will be well versed with deep learning and its implementation with Keras. You will have all the knowledge you need to train your own deep learning models to solve different kinds of problems. What you will learn *Apply regression methods to your data and understand how the regression algorithm works *Understand the basic concepts of classification methods and how to implement them in the Keras environment *Import and organize data for neural network classification analysis *Learn about the role of rectified linear units in the Keras network architecture *Implement a recurrent neural network to classify the sentiment of sentences from movie reviews *Set the embedding layer and the tensor sizes of a network Who this book is for If you are a data scientist, machine learning engineer, deep learning practitioner or an AI engineer who wants to build speedy intelligent applications with minimal lines of codes, then this book is the best fit for you. Sound knowledge of machine learning and basic familiarity with Keras library would be useful.

目录

Title Page

Copyright and Credits

Keras 2.x Projects

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

Get in touch

Reviews

Getting Started with Keras

Introduction to Keras

Keras backend options

TensorFlow

Theano

CNTK

Installation

Optional dependencies

Installing the backend engine

Keras installation and configuration

Model fitting in Keras

The Keras sequential model architecture

Keras functional API model architecture

Summary

Modeling Real Estate Using Regression Analysis

Defining a regression problem

Basic regression concepts

Different types of regression

Creating a linear regression model

Multiple linear regression concepts

Neural networks for regression using Keras

Exploratory analysis

Data splitting

Neural network Keras model

Multiple linear regression model

Summary

Heart Disease Classification with Neural Networks

Basics of classification problems

Different types of classification

Classification algorithms

Naive Bayes algorithm

Gaussian mixture models

Discriminant analysis

K-nearest neighbors

Support vector machine

Bayesian decision theory

Bayes' theorem

Pattern recognition using a Keras neural network

Exploratory analysis

Handling missing data in Python

Data scaling

Data visualization

Keras binary classifier

Summary

Concrete Quality Prediction Using Deep Neural Networks

Basic concepts of ANNs

Architecture of ANNs

Learning paradigms

Supervised learning

Unsupervised learning

Semi-supervised learning

Understanding the structure of neural networks

Weights and biases

Types of activation functions

Unit step activation function

Sigmoid

Hyperbolic tangent

Rectified linear unit

Multilayer neural networks

Implementing multilayer neural networks in Keras

Exploratory analysis

Data visualization

Data scaling

Building a Keras deep neural network model

Improving the model performance by removing outliers

Summary

Fashion Article Recognition Using Convolutional Neural Networks

Understanding computer vision concepts

Convolutional neural networks

Convolution layer

Pooling layers

Rectified linear units

Fully connected layer

Structure of a CNN

Common CNN architecture

LeNet-5

AlexNet

ResNet

VGG Net

GoogleNet

Implementing a CNN for object recognition

Exploratory analysis

Data scaling

Using Keras in the CNN model

Exploring the model's results

Summary

Movie Reviews Sentiment Analysis Using Recurrent Neural Networks

Sentiment analysis basic concepts

Sentiment analysis techniques

The next challenges for sentiment analysis

Lexicon and semantics analysis

Recurrent neural networks

Fully recurrent neural networks

Recursive neural networks

Hopfield recurrent neural networks

Elman neural networks

Long short-term memory network

Classifying sentiment in movie reviews using an RNN

IMDB Movie reviews dataset

Exploratory analysis

Keras recurrent neural network model

Exploring model results

Summary

Stock Volatility Forecasting Using Long Short-Term Memory

The basics of forecasting

Forecast horizon

Forecasting methods

Quantitative methods

Qualitative methods

Time series analysis

The classical approach to time series

Estimation of the trend component

Estimating the seasonality component

Time series models

Autoregressive models

Moving average models

Autoregressive moving average model

Autoregressive integrated moving average models

Long short-term memory in Keras

Implementing an LSTM to forecast stock volatility

Exploratory analysis

Data scaling

Data splitting

Keras LSTM model

Summary

Reconstruction of Handwritten Digit Images Using Autoencoders

Basic concepts of image recognition

Image digitization

Image recognition

Optical character recognition

Approaches to the problem

Generative neural networks

The restricted Boltzmann machine

Autoencoders

Variational autoencoders

The generative adversarial network

The adversarial autoencoder

The Keras autoencoders model

Implementing autoencoder Keras layers to reconstruct handwritten digit images

The MNIST dataset

Min–max normalization

Keras model architecture

Exploring model results

Summary

Robot Control System Using Deep Reinforcement Learning

Robot control overview

Three laws of robotics

Short robotics timeline

First-generation robots

Second-generation robots

Third-generation robots

Fourth-generation robots

Automatic control

The environment for controlling robot mobility

OpenAI Gym

Reinforcement learning basics

Agent-environment interface

Reinforcement learning algorithms

Dynamic Programming

Monte Carlo methods

Temporal difference learning

Keras DQNs

Q-learning

Deep Q-learning

Keras-RL library

DQN to control a robot's mobility

OpenAI Gym installation and methods

The CartPole system

Q-learning solution

Deep Q-learning solution

Summary

Reuters Newswire Topics Classifier in Keras

Natural language processing

NLP phases

Morphology analysis

Syntax analysis

Semantic analysis

Pragmatic analysis

Automatic processing problems

NLP applications

Information retrieval

Information extraction

Question-answering

Automatic summarization

Automatic translation

Sentiment analysis

NLP methods

Sentence splitting

Tokenization

Part-of-speech tagging

Shallow parsing

Named entity recognition

Syntactic parsing

Semantic role labeling

Natural language processing tools

The Natural Language Toolkit

The Stanford NLP Group software

Apache OpenNLP

GATE

The Natural Language Toolkit

Getting started with the NLTK

Corpora

Brown corpus

Word and sentence tokenize

Part-of-speech tagger

Stemming and lemmatization

Stemming

Lemmatization

Implementing a DNN to label sentences

Exploratory analysis

Data preparation

Keras deep neural network model

Summary

What is Next?

Deep learning methods

Deep feedforward network

Convolutional neural networks

Recurrent neural networks

Long short-term memory

Restricted Boltzmann machine

Deep belief network

Generative adversarial networks

Automated machine learning

Auto-Keras

Google Cloud ML Engine

Azure Machine Learning Studio

Amazon Web Services

Differentiable neural computer

Genetic programming and evolutionary strategies

Introducing the genetic algorithm

The fitness function

Selection

Mutation

Inverse reinforcement learning

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think