万本电子书0元读

万本电子书0元读

顶部广告

Applied Deep Learning with Keras电子书

售       价:¥

15人正在读 | 0人评论 6.8

作       者:Ritesh Bhagwat

出  版  社:Packt Publishing

出版时间:2019-04-24

字       数:658.6万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:此类商品不支持退换货,不支持下载打印

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)
Take your neural networks to a whole new level with the simplicity and modularity of Keras, the most commonly used high-level neural networks API. Key Features * Solve complex machine learning problems with precision * Evaluate, tweak, and improve your deep learning models and solutions * Use different types of neural networks to solve real-world problems Book Description Though designing neural networks is a sought-after skill, it is not easy to master. With Keras, you can apply complex machine learning algorithms with minimum code. Applied Deep Learning with Keras starts by taking you through the basics of machine learning and Python all the way to gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. To help you grasp the difference between machine and deep learning, the book guides you on how to build a logistic regression model, first with scikit-learn and then with Keras. You will delve into Keras and its many models by creating prediction models for various real-world scenarios, such as disease prediction and customer churning. You’ll gain knowledge on how to evaluate, optimize, and improve your models to achieve maximum information. Next, you’ll learn to evaluate your model by cross-validating it using Keras Wrapper and scikit-learn. Following this, you’ll proceed to understand how to apply L1, L2, and dropout regularization techniques to improve the accuracy of your model. To help maintain accuracy, you’ll get to grips with applying techniques including null accuracy, precision, and AUC-ROC score techniques for fine tuning your model. By the end of this book, you will have the skills you need to use Keras when building high-level deep neural networks. What you will learn * Understand the difference between single-layer and multi-layer neural network models * Use Keras to build simple logistic regression models, deep neural networks, recurrent neural networks, and convolutional neural networks * Apply L1, L2, and dropout regularization to improve the accuracy of your model * Implement cross-validate using Keras wrappers with scikit-learn * Understand the limitations of model accuracy Who this book is for If you have basic knowledge of data science and machine learning and want to develop your skills and learn about artificial neural networks and deep learning, you will find this book useful. Prior experience of Python programming and experience with statistics and logistic regression will help you get the most out of this book. Although not necessary, some familiarity with the scikit-learn library will be an added bonus.
目录展开

Preface

About the Book

About the Authors

Learning Objectives

Audience

Approach

Hardware Requirements

Software Requirements

Conventions

Installation and Setup

Installing the Code Bundle

Additional Resources

Chapter 1

Introduction to Machine Learning with Keras

Introduction

Data Representation

Tables of Data

Loading Data

Exercise 1: Loading a Dataset from the UCI Machine Learning Repository

Data Preprocessing

Exercise 2: Cleaning the Data

Appropriate Representation of the Data

Exercise 3: Appropriate Representation of the Data

Life Cycle of Model Creation

Machine Learning Libraries

scikit-learn

Keras

Advantages of Keras

Disadvantages of Keras

More than Building Models

Model Training

Classifiers and Regression Models

Classification Tasks

Regression Tasks

Training and Test Datasets

Model Evaluation Metrics

Exercise 4: Creating a Simple Model

Model Tuning

Baseline Models

Exercise 5: Determining a Baseline Model

Regularization

Cross-Validation

Activity 1: Adding Regularization to the Model

Summary

Chapter 2

Machine Learning versus Deep Learning

Introduction

Advantages of ANNs over Traditional Machine Learning Algorithms

Advantages of Traditional Machine Learning Algorithms over ANNs

Hierarchical Data Representation

Linear Transformations

Scalars, Vectors, Matrices, and Tensors

Tensor Addition

Exercise 6: Perform Various Operations with Vectors, Matrices, and Tensors

Reshaping

Matrix Transposition

Exercise 7: Matrix Reshaping and Transposition

Matrix Multiplication

Exercise 8: Matrix Multiplication

Exercise 9: Tensor Multiplication

Introduction to Keras

Layer Types

Activation Functions

Model Fitting

Activity 2: Creating a Logistic Regression Model Using Keras

Summary

Chapter 3

Deep Learning with Keras

Introduction

Building Your First Neural Network

Logistic Regression to a Deep Neural Network

Activation Functions

Forward Propagation for Making Predictions

Loss Function

Backpropagation for Computing Derivatives of Loss Function

Gradient Descent for Learning Parameters

Exercise 10: Neural Network Implementation with Keras

Activity 3: Building a Single-Layer Neural Network for Performing Binary Classification

Model Evaluation

Evaluating a Trained Model with Keras

Splitting Data into Training and Test Sets

Underfitting and Overfitting

Early Stopping

Activity 4: Diabetes Diagnosis with Neural Networks

Summary

Chapter 4

Evaluate Your Model with Cross-Validation using Keras Wrappers

Introduction

Cross-Validation

Drawbacks of Splitting a Dataset Only Once

K-Fold Cross-Validation

Leave-One-Out Cross-Validation

Comparing the K-Fold and LOO Methods

Cross-Validation for Deep Learning Models

Keras Wrapper with scikit-learn

Exercise 11: Building the Keras Wrapper with scikit-learn for a Regression Problem

Cross-Validation with scikit-learn

Cross-Validation Iterators in scikit-learn

Exercise 12: Evaluate Deep Neural Networks with Cross-Validation

Activity 5: Model Evaluation Using Cross-Validation for a Diabetes Diagnosis Classifier

Model Selection with Cross-validation

Cross-Validation for Model Evaluation versus Model Selection

Exercise 13: Write User-Defined Functions to Implement Deep Learning Models with Cross-Validation

Activity 6: Model Selection Using Cross-Validation for the Diabetes Diagnosis Classifier

Activity 7: Model Selection Using Cross-validation on the Boston House Prices Dataset

Summary

Chapter 5

Improving Model Accuracy

Introduction

Regularization

The Need for Regularization

Reducing Overfitting with Regularization

L1 and L2 Regularization

L1 and L2 Regularization Formulation

L1 and L2 Regularization Implementation in Keras

Activity 8: Weight Regularization on a Diabetes Diagnosis Classifier

Dropout Regularization

Principles of Dropout Regularization

Reducing Overfitting with Dropout

Exercise 14: Dropout Implementation in Keras

Activity 9: Dropout Regularization on Boston Housing Dataset

Other Regularization Methods

Early Stopping

Exercise 15: Implementing Early Stopping in Keras

Data Augmentation

Adding Noise

Hyperparameter Tuning with scikit-learn

Grid Search with scikit-learn

Randomized Search with scikit-learn

Activity 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier

Summary

Chapter 6

Model Evaluation

Introduction

Accuracy

Exercise 16: Calculating Null Accuracy on a Dummy Healthcare Dataset

Advantages and Limitations of Accuracy

Imbalanced Datasets

Working with Imbalanced Datasets

Confusion Matrix

Metrics Computed from a Confusion Matrix

Exercise 17: Computing Accuracy and Null Accuracy with Healthcare Data

Activity 11: Computing the Accuracy and Null Accuracy of a Neural Network When We Change the Train/Test Split

Activity 12: Derive and Compute Metrics Based on a Confusion Matrix

Exercise 18: Calculate the ROC and AUC Curves

Summary

Chapter 7

Computer Vision with Convolutional Neural Networks

Introduction

Computer Vision

Convolutional Neural Networks

Architecture of a CNN

Input Image

Convolution Layer

Pooling Layer

Flattening

Image Augmentation

Advantages of Image Augmentation

Exercise 19: Build a CNN and Identify Images of Cats and Dogs

Activity 13: Amending our Model with Multiple Layers and the Use of SoftMax

Exercise 20: Amending our model by reverting to the Sigmoid activation function

Exercise 21: Changing the Optimizer from Adam to SGD

Exercise 22: Classifying a New Image

Activity 14: Classify a New Image

Summary

Chapter 8

Transfer Learning and Pre-Trained Models

Introduction

Pre-Trained Sets and Transfer Learning

Feature Extraction

Fine-Tuning a Pre-Trained Network

The ImageNet Dataset

Some Pre-Trained Networks in Keras

Exercise 23: Identify an Image Using the VGG16 Network

Activity 15: Use the VGG16 Network to Train a Deep Learning Network to Identify Images

Exercise 24: Classification of Images That Are Not Present in the ImageNet Database.

Exercise 25: Fine-Tune the VGG16 Model

Exercise 26: Image Classification with ResNet

Activity 16: Image Classification with ResNet

Summary

Chapter 9

Sequential Modeling with Recurrent Neural Networks

Introduction

Sequential Memory and Sequential Modeling

Recurrent Neural Networks (RNNs)

The Vanishing Gradient Problem

Long Short-Term Memory (LSTM)

Exercise 27: Predict the Trend of Apple's Stock Price Using an LSTM with 50 Units (Neurons)

Activity 17: Predict the Trend of Microsoft's Stock Price Using an LSTM with 50 Units (Neurons)

Exercise 28: Predicting the Trend of Apple's Stock Price Using an LSTM with 100 units

Activity 18: Predicting Microsoft's Stock Price with Added Regularization

Activity 19: Predicting the Trend of Microsoft's Stock Price Using an LSTM with an Increasing Number of LSTM Neurons (100 Units)

Summary

Appendix

Chapter 1: Introduction to Machine Learning with Keras

Activity 1: Adding Regularization to the Model

Chapter 2: Machine Learning versus Deep Learning

Activity 2: Creating a Logistic Regression Model Using Keras

Chapter 3: Deep Learning with Keras

Activity 3: Building a Single-Layer Neural Network for Performing Binary Classification

Activity 4: Diabetes Diagnosis with Neural Networks

Chapter 4: Evaluate Your Model with Cross-Validation with Keras Wrappers

Activity 5: Model Evaluation Using Cross-Validation for a Diabetes Diagnosis Classifier

Activity 6: Model Selection Using Cross-Validation for the Diabetes Diagnosis Classifier

Activity 7: Model Selection Using Cross-validation on the Boston House Prices Dataset

Chapter 5: Improving Model Accuracy

Activity 8: Weight Regularization on a Diabetes Diagnosis Classifier

Activity 9: Dropout Regularization on Boston House Prices Dataset

Activity 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier

Chapter 6: Model Evaluation

Activity 11: Computing Accuracy and Null Accuracy of Neural Network When We Change the Train/Test Split

Activity 12: Derive and Compute Metrics Based on the Confusion Matrix

Chapter 7: Computer Vision with Convolutional Neural Networks

Activity 13: Amending our Model with Multiple Layers and Use of SoftMax

Activity 14: Classify a New Image

Chapter 8: Transfer Learning and Pre-trained Models

Activity 15: Use the VGG16 Network to Train a Deep Learning Network to Identify Images

Activity 16: Image Classification with ResNet

Chapter 9: Sequential Modeling with Recurrent Neural Networks

Activity 17: Predict the Trend of Microsoft’s Stock Price Using an LSTM with 50 Units (Neurons)

Activity 18: Predicting Microsoft’s stock price with added regularization

Activity 19: Predicting the Trend of Microsoft’s Stock Price Using LSTM with 100 Units

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