logo资料库

Deep Time Series Forecasting with Python.pdf

发布时间：2022-06-15 发布人：admin 分类：说明书 资料大小：1.65M 资料格式：pdf 举报 版权申诉
第1页 / 共212页
第2页 / 共212页
第3页 / 共212页
第4页 / 共212页
第5页 / 共212页
第6页 / 共212页
第7页 / 共212页
第8页 / 共212页
资料共212页，剩余部分请下载后查看
    Contents
    Contents continued
    Contents continued
    Other Books You Will Also Enjoy
    Preface
    A Promise
    How to Get the Most from this Book
    Chapter 1 The Characteristics of Time Series Data Simplified
    Chapter 2 Deep Neural Networks Explained
    Chapter 3 Deep Neural Networks for Time Series Forecasting the Easy Way
    Chapter 4 A Simple Way to Incorporate Additional Attributes in Your Model
    Chapter 5 The Simple Recurrent Neural Network
    Chapter 6 Elman Neural Networks
    Chapter 7 Jordan Neural Networks
    Chapter 8 Nonlinear Auto-regressive Network with Exogenous Inputs
    Chapter 9 Long Short-Term Memory Recurrent Neural Network
    Chapter 10 Gated Recurrent Un
    Chapter 11 Forecasting Multiple Outputs
    Chapter 12 Strategies to Build Superior Models
    A Special Message for YOU
    Ego autem et domus mea serviemus Domino.
    DEEP TIME SERIES FORECASTING With PYTHON An Intuitive Introduction to Deep Learn- ing for Applied Time Series Modeling Dr. N.D Lewis
    Copyright © 2016 by N.D. Lewis All rights reserved. No part of this publication may be reproduced, dis- tributed, or transmitted in any form or by any means, including photo- copying, recording, or other electronic or mechanical methods, without the prior written permission of the author, except in the case of brief quo- tations embodied in critical reviews and certain other noncommercial uses permitted by copyright law. For permission requests, contact the author at: www.AusCov.com. Disclaimer: Although the author and publisher have made every effort to ensure that the information in this book was correct at press time, the author and publisher do not assume and hereby disclaim any liability to any party for any loss, damage, or disruption caused by errors or omissions, whether such errors or omissions result from negligence, accident, or any other cause. Ordering Information: Quantity sales. Special discounts are available on quantity purchases by corporations, associations, and others. For details, email: info@NigelDLewis.com Image photography by Deanna Lewis with helpful assistance from Naomi Lewis. ISBN-13: 978-1540809087 ISBN-10: 1540809080
    Contents Acknowledgements Preface How to Get the Absolute Most Possible Benefit from this Book Getting Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Learning Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Using Packages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 1 The Characteristics of Time Series Data Simplified Understanding the Data Generating Mechanism . . . . . . . . . . . . . . . . . Generating a Simple Time Series using Python . . . . . . . . . . . . . . . . . Randomness and Reproducibility . . . . . . . . . . . . . . . . . . . . . . . . The Importance of Temporal Order . . . . . . . . . . . . . . . . . . . . . . . . The Ultimate Goal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . For Additional Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 Deep Neural Networks Explained What is a Neural Network? . . . . . . . . . . . . . . . . . . . . . . . . . . . . The Role of Neuron . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Deep Learning in a Nutshell . . . . . . . . . . . . . . . . . . . . . . . . . . . . Generating Data for use with a Deep Neural Network . . . . . . . . . . . . . Exploring the Sample Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . Translating Sample Data into a Suitable Format . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . A Super Easy Deep Neural Network Tool Assessing Model Performance . . . . . . . . . . . . . . . . . . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 3 Deep Neural Networks for Time Series Forecasting the Easy Way Getting the Data from the Internet . . . . . . . . . . . . . . . . . . . . . . . Cleaning up Downloaded Spreadsheet Files . . . . . . . . . . . . . . . . . . . Understanding Activation Functions . . . . . . . . . . . . . . . . . . . . . . . How to Scale the Input attributes . . . . . . . . . . . . . . . . . . . . . . . . Assessing Partial Autocorrelation . . . . . . . . . . . . . . . . . . . . . . . . . A Neural Network Architecture for Time Series Forecasting . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . i iii viii 1 3 3 4 5 7 7 9 12 13 14 15 17 17 18 19 21 22 25 26 28 30 31 31 33 36 39 42 45 49
    4 A Simple Way to Incorporate Additional Attributes in Your Model 51 51 54 56 58 59 60 62 66 Working with Additional Attributes . . . . . . . . . . . . . . . . . . . . . . . The Working of the Neuron Simplified . . . . . . . . . . . . . . . . . . . . . . How a Neural Network Learns . . . . . . . . . . . . . . . . . . . . . . . . . . . Gradient Descent Clarified . . . . . . . . . . . . . . . . . . . . . . . . . . . . . How to Easily Specify a Model . . . . . . . . . . . . . . . . . . . . . . . . . . Choosing a Learning Rate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . The Efficient Way to Run Your Model . . . . . . . . . . . . . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 5 The Simple Recurrent Neural Network Why Use Keras? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . What is a Recurrent Neural Network? . . . . . . . . . . . . . . . . . . . . . . Gain Clarity on the Role of the Delay Units . . . . . . . . . . . . . . . . . . . Follow this Approach to Create Your Train and Test Sets . . . . . . . . . . . Parameter Sharing Clarified . . . . . . . . . . . . . . . . . . . . . . . . . . . . Understand Backpropagation Through Time . . . . . . . . . . . . . . . . . . A Complete Intuitive Guide to Momentum . . . . . . . . . . . . . . . . . . . How to Benefit from Mini Batching . . . . . . . . . . . . . . . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 6 Elman Neural Networks Prepare You Data for Easy Use . . . . . . . . . . . . . . . . . . . . . . . . . . How to Model a Complex Mathematical Relationship with No Knowledge . . Use this Python Library for Rapid Results . . . . . . . . . . . . . . . . . . . . Exploring the Error Surface . . . . . . . . . . . . . . . . . . . . . . . . . . . . A Super Simple Way to Fit the Model . . . . . . . . . . . . . . . . . . . . . . Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 67 67 68 71 72 73 73 76 78 81 83 84 85 88 89 91 93 7 Jordan Neural Networks 95 96 The Fastest Path to Data Preparation . . . . . . . . . . . . . . . . . . . . . . 97 A Straightforward Module for Jordan Neural Networks . . . . . . . . . . . . . Assessing Model Fit and Performance . . . . . . . . . . . . . . . . . . . . . . 98 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 100 8 Nonlinear Auto-regressive Network with Exogenous Inputs 103 What is a NARX Network? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103 Spreadsheet Files Made Easy with Pandas . . . . . . . . . . . . . . . . . . . . 105 Working with Macroeconomic Variables . . . . . . . . . . . . . . . . . . . . . 107 Python and Pandas Data Types . . . . . . . . . . . . . . . . . . . . . . . . . 111 A Tool for Rapid NARX Model Construction . . . . . . . . . . . . . . . . . . 113 How to Run the Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 115 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 117 9 Long Short-Term Memory Recurrent Neural Network 119 Cyclical Patterns in Time Series Data . . . . . . . . . . . . . . . . . . . . . . 119 What is an LSTM? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 122 Efficiently Explore and Quickly Understand Data . . . . . . . . . . . . . . . . 123 The LSTM Memory Block in a Nutshell . . . . . . . . . . . . . . . . . . . . . 127 Straightforward Data Transformation for the Train and Test Sets . . . . . . . 128 Clarify the Role of Gates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 130 Understand the Constant Error Carousel . . . . . . . . . . . . . . . . . . . . . 131 Specifying a LSTM Model the Easy Way . . . . . . . . . . . . . . . . . . . . 132 Shuffling Examples to Improve Generalization . . . . . . . . . . . . . . . . . . 136 A Note on Vanishing Gradients . . . . . . . . . . . . . . . . . . . . . . . . . . 138
    Follow these Steps to Build a Stateful LSTM . . . . . . . . . . . . . . . . . . 139 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 144 10 Gated Recurrent Unit 145 The Gated Recurrent Unit in a Nutshell . . . . . . . . . . . . . . . . . . . . . 145 A Simple Approach to Gated Recurrent Unit Construction . . . . . . . . . . 148 A Quick Recap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 150 How to Use Multiple Time Steps . . . . . . . . . . . . . . . . . . . . . . . . . 151 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 154 11 Forecasting Multiple Outputs 155 Working with Zipped Files . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 156 How to Work with Multiple Targets . . . . . . . . . . . . . . . . . . . . . . . 159 Creation of Hand Crafted Features . . . . . . . . . . . . . . . . . . . . . . . . 161 Model Specification and Fit . . . . . . . . . . . . . . . . . . . . . . . . . . . . 163 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 166 12 Strategies to Build Superior Models 169 Revisiting the UK Unemployment Rate Economic Data . . . . . . . . . . . . 169 Limitations of the Sigmoid Activation Function . . . . . . . . . . . . . . . . . 171 One Activation Function You Need to Add to Your Deep Learning Toolkit . . 172 Try This Simple Idea to Enhance Success . . . . . . . . . . . . . . . . . . . . 176 A Simple Plan for Early Stopping . . . . . . . . . . . . . . . . . . . . . . . . . 180 Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 184 Index 189
    分享到：
    赞 收藏

    相关推荐

    资料库

    后端

    共收录2142份资料，累计10个分类，关注成员有19位，主要包括：Perl,Docker,Delphi,VB,PHP,Java,C,C#,Python,C++

    热门标签

    Perl Docker Delphi VB PHP Java C C# Python C++

    最新资料