Machine Learning and Deep Learning Using Python and TensorFlow / Shailendra Kadre, Venkata Reddy Konasani.

Format:

Book

Author/Creator:

Kadre, Shailendra, author.

Reddy Konasani, Venkata, author.

Series:

McGraw-Hill's AccessEngineering

Language:

English

Subjects (All):

Machine learning.

Genre:

Electronic books.

Physical Description:

1 online resource

Edition:

First edition.

Place of Publication:

New York, N.Y. : McGraw-Hill Education, [2021]

Language Note:

In English.

Summary:

This book provides you with an in-depth treatment of some advanced machine learning methods such as random forests, boosting, and neural networks.

Contents:

Cover

Title Page

Copyright Page

Dedication

About the Authors

Contents

Acknowledgments

Preface

Chapter 1. Introduction to Machine Learning and Deep Learning

1.1 A Brief History of AI and Machine Learning

1.2 Building Blocks of a Machine Learning Project

1.3 Machine Learning Algorithms vs. Traditional Computer Programs

1.4 How Deep Learning Works

1.5 Machine Learning and Deep Learning Applications

1.6 The Organization of This Book

1.7 Prerequisites?Essential Mathematics

1.8 The Terminology You Should Know

1.9 Machine Learning?A Wider Outlook Will Certainly Help

1.10 Python and Its Potential as the Language of Machine Learning

1.11 About TensorFlow

1.12 Conclusion

1.13 References

Chapter 2. Basics of Python Programming and Statistics

2.1 Introduction to Python

2.2 Getting Started with Python Coding

2.3 Types of Objects in Python

2.4 Python Packages

2.5 Conditions and Loops in Python

2.6 Data Handling and Pandas Deep Dive

2.7 Basic Descriptive Statistics

2.8 Data Exploration

2.9 Conclusion

2.10 Practice Problems

2.11 References

Chapter 3. Regression and Logistic Regression

3.1 What Is Regression?

3.2 Regression Model Building

3.3 R-Squared

3.4 Multiple Regression

3.5 Multicollinearity in Regression

3.6 Individual Impact of the Variables in Regression

3.7 Steps Needed in Building a Regression Model

3.8 Logistic Regression Model

3.9 Logistic Regression Model Building

3.10 Accuracy of Logistic Regression Line

3.11 Multiple Logistic Regression Line

3.12 Multicollinearity in Logistic Regression

3.13 Individual Impact of the Variables

3.14 Steps in Building a Logistic Regression Model

3.15 Linear vs. Logistic Regression Comparison

3.16 Conclusion

3.17 Practice Problems

3.18 Reference

Chapter 4. Decision Trees

4.1 What Are Decision Trees?

4.2 Splitting Criterion Metrics: Entropy and Information Gain

4.3 Decision Tree Algorithm

4.4 Case Study: Contact Center Customer Segmentation

4.5 The Problem of Overfitting

4.6 Pruning of Decision Trees

4.7 The Challenge of Underfitting

4.8 Binary Search on Pruning Parameters

4.9 More Pruning Parameters

4.10 Steps in Building a Decision Tree Model

4.11 Conclusion

4.12 Practice Problems

Chapter 5. Model Selection and Cross-Validation

5.1 Steps in Building a Model

5.2 Model Validation Measures: Regression

5.3 Case Study: House Sales in King County, Washington

5.4 Model Validation Measures: Classification

5.5 Bias-Variance Trade-Off

5.6 Cross-Validation

5.7 Feature Engineering Tips and Tricks

5.8 Dealing with Class Imbalance

5.9 Conclusion

5.10 Practice Problems

5.11 References

Chapter 6. Cluster Analysis

6.1 Unsupervised Learning

6.2 Distance Measure

6.3 K-Means Clustering Algorithm

6.4 Building K-Means Clusters

6.5 Deciding the Number of Clusters

6.6 Conclusion

6.7 Practice Problems

6.8 References

Chapter 7. Random Forests and Boosting

7.1 Ensemble Models

7.2 Bagging

7.3 Random Forest

7.4 Case Study: Car Accidents Prediction

7.5 Boosting

7.6 AdaBoosting Algorithm

7.7 Gradient Boosting Algorithm

7.8 Case Study: Income Prediction from Census Data

7.9 Conclusion

7.10 Practice Problems

7.11 References

Chapter 8. Artificial Neural Networks

8.1 Network Diagram for Logistic Regression

8.2 Concept of Decision Boundary

8.3 Multiple Decision Boundaries Problem

8.4 Multiple Decision Boundaries Solution

8.5 Neural Network Intuition

8.6 Neural Network Algorithm

8.7 The Concept of Gradient Descent

8.8 Case Study: Recognizing Handwritten Digits

8.9 Deep Neural Networks

8.10 Conclusion

8.11 Practice Problems

8.12 References

Chapter 9. TensorFlow and Keras

9.1 Deep Neural Networks

9.2 Deep Learning Frameworks

9.3 Key Terms in TensorFlow

9.4 Model Building with TensorFlow

9.5 Keras

9.6 Conclusion

9.7 References

Chapter 10. Deep Learning Hyperparameters

10.1 Regularization

10.2 Dropout Regularization

10.3 Early Stopping Method

10.4 Loss Functions

10.5 Activation Functions

10.6 Learning Rate

10.7 Optimizers

10.8 Conclusion

Chapter 11. Convolutional Neural Networks

11.1 ANNs for Images

11.2 Filters

11.3 The Convolution Layer

11.4 Pooling Layer

11.5 CNN Architecture

11.6 Case Study: Sign Language Reading from Images

11.7 Scheming the Ideal CNN Architecture

11.8 Steps in Building a CNN Model

11.9 Conclusion

11.10 Practice Problems

11.11 References

Chapter 12. Recurrent Neural Networks and Long Short-Term Memory

12.1 Cross-Sectional Data vs. Sequential Data

12.2 Models for Sequential Data

12.3 Case Study: Word Prediction

12.4 Recurrent Neural Networks

12.5 RNN for Long Sequences

12.6 Long Short-Term Memory

12.7 Sequence to Sequence Models

12.8 Case Study: Language Translation

12.9 Conclusion

12.10 Practice Problems

12.11 References

Index.

Notes:

Includes bibliographical references and index.

Electronic reproduction. New York, N.Y. : McGraw Hill, 2021. Mode of access: World Wide Web. System requirements: Web browser. Access may be restricted to users at subscribing institutions.

Description based on e-Publication PDF.

Other Format:

Print version: Machine Learning and Deep Learning Using Python and TensorFlow.

ISBN:

9781260462302 (e-ISBN)

1260462307 (e-ISBN)

9781260462296 (print-ISBN)

1260462293 (print-ISBN)

OCLC:

1245575418

Access Restriction:

Restricted for use by site license.