book

Machine Learning and AI with Simple Python and Matlab Scripts

Name: Machine Learning and AI with Simple Python and Matlab Scripts
Author: M. Umit Uyar
ISBN: 9781394294954

by M. Umit Uyar

April 2025

Intermediate

384 pages

11h 15m

English

Wiley-IEEE Press

Read now

Unlock full access

Cover
Table of Contents
Title Page
Copyright
Dedication
About the Author
Preface
Acknowledgments
About the Companion Website
1 Introduction
1.1 Artificial Intelligence1.2 A Historical Perspective1.3 Principles of AI1.4 Applications That Are Impossible Without AI1.5 Organization of This Book

2 Artificial Neural Networks
2.1 Introduction2.2 Applications of ANNs2.3 Components of ANNs2.4 Training an ANN2.5 Forward Propagation2.6 Back Propagation2.7 Updating Weights2.8 ANN with Input Bias2.9 A Simple Algorithm for ANN Training2.10 Computational Complexity of ANN Training2.11 Normalization of ANN Inputs and Outputs2.12 Concluding Remarks2.13 Exercises for Chapter 2
3 ANNs for Optimized Prediction
3.1 Introduction3.2 Selection of ANN Inputs3.3 Selection of ANN Outputs3.4 Construction of Hidden Layers3.5 Case Study 1: Sleep‐Study Example3.6 Case Study 2: Prediction of Bike Rentals3.7 Concluding Remarks3.8 Exercises for Chapter 3
4 ANNs for Financial Stock Trading
4.1 Introduction4.2 Programs that Buy and Sell Stocks4.3 Technical Indicators4.4 A Simple Algorithmic Trading Policy4.5 A Simple ANN for Algorithmic Stock Trading4.6 Python Script for Stock Trading Using an ANN4.7 Matlab Script for Stock Trading Using an ANN4.8 Concluding Remarks4.9 Exercises for Chapter 4
5 ANNs for Alzheimer's Disease Prognosis
5.1 Introduction5.2 Alzheimer's Disease5.3 A Simple ANN for AD Prognosis5.4 Python Script for AD Prognosis Using an ANN5.5 Matlab Script for AD Prognosis Using an ANN5.6 Concluding Remarks5.7 Exercises for Chapter 5
6 ANNs for Natural Language Processing
6.1 Introduction6.2 Impact of Text Messages on Stock Markets6.3 A Simple ANN for NLP6.4 Python Script for NLP Using an ANN6.5 Matlab Script for NLP Using an ANN6.6 Concluding Remarks6.7 Exercises for Chapter 6
7 Convolutional Neural Networks
7.1 Introduction7.2 Variations of CNNs7.3 Applications of CNNs7.4 CNN Components7.5 A Numerical Example of a CNN7.6 Computational Cost of CNN Training7.7 Concluding Remarks7.8 Exercises for Chapter 7
8 CNNs for Optical Character Recognition
8.1 Introduction8.2 A Simple CNN for OCR8.3 Organization of Training and Reference Files8.4 Python Script for OCR Using a CNN8.5 Matlab Script for OCR Using a CNN8.6 Concluding Remarks8.7 Exercises for Chapter 8
9 CNNs for Speech Recognition
9.1 Introduction9.2 A Simple CNN for Speech Recognition9.3 Organization of Training and Reference Files9.4 Python Script for Speech Recognition Using a CNN9.5 Matlab Script for Speech Recognition Using a CNN9.6 Concluding Remarks9.7 Exercises for Chapter 9
10 Recurrent Neural Networks
10.1 Introduction10.2 One‐to‐One Single RNN Cell10.3 A Numerical Example10.4 Multiple Hidden Layers10.5 Embedding Layer10.6 Concluding Remarks10.7 Exercises for Chapter 10
11 RNNs for Chatbot Implementation
11.1 Introduction11.2 Many‐to‐Many RNN Architecture11.3 A Simple Chatbot11.4 Python Script for a Chatbot Using an RNN11.5 Matlab Script for a Chatbot Using an RNN11.6 Concluding Remarks11.7 Exercises for Chapter 11
12 RNNs with Attention
12.1 Introduction12.2 One‐to‐One RNN Cell with Attention12.3 Forward and Back Propagation12.4 A Numerical Example12.5 Embedding Layer12.6 A Numerical Example with Embedding12.7 Concluding Remarks12.8 Exercises for Chapter 12
13 RNNs with Attention for Machine Translation
13.1 Introduction13.2 Many‐to‐Many Architecture13.3 Python Script for Machine Translation by an RNN‐Att13.4 Matlab Script for Machine Translation by an RNN‐Att13.5 Concluding Remarks13.6 Exercises for Chapter 13
14 Genetic Algorithms
14.1 Introduction14.2 Genetic Algorithm Elements14.3 A Simple Algorithm for a GA14.4 An Example of a GA14.5 Convergence in GAs14.6 Concluding Remarks14.7 Exercises for Chapter 14
15 GAs for Dietary Menu Selection
15.1 Introduction15.2 Definition of the KP15.3 A Simple Algorithm for the KP15.4 Variations of the KP15.5 GAs for KP Solution15.6 Python Script for Dietary Menu Selection Using a GA15.7 Matlab Script for Dietary Menu Selection Using a GA15.8 Concluding Remarks15.9 Exercises for Chapter 15Note
16 GAs for Drone Flight Control
16.1 Introduction16.2 UAV Swarms16.3 UAV Flight Control16.4 A Simple GA for UAV Flight Control16.5 Python Script for UAV Flight Control Using a GA16.6 Matlab Script for UAV Flight Control Using a GA16.7 Concluding Remarks16.8 Exercises for Chapter 16
17 GAs for Route Optimization
17.1 Introduction17.2 Definition of the TSP17.3 A Simple Algorithm for the TSP17.4 Variations of the TSP17.5 GA Solution for the TSP17.6 Python Script for Route Optimization Using a GA17.7 Matlab Script for Route Optimization Using a GA17.8 Concluding Remarks17.9 Exercises for Chapter 17
18 Evolutionary Methods
18.1 Introduction18.2 Particle Swarm Optimization18.3 Differential Evolution18.4 Grammatical Evolution
Appendix A: ANNs with BiasANNs with Bias
A.1 IntroductionA.2 Training with Bias InputA.3 Forward Propagation
Appendix B: Sleep Study ANN with BiasSleep Study ANN with Bias
B.1 Inclusion of Bias Term in ANN
Appendix C: Back Propagation in a CNNBack Propagation in a CNN
Appendix D: Back Propagation Through Time in an RNNBack Propagation Through Time in an RNN
D.1 Back Propagation in an RNND.2 Embedding Layer
Appendix E: Back Propagation Through Time in an RNN with AttentionBack Propagation Through Time in an RNN with Attention
E.1 Back Propagation in an RNN‐AttE.2 Embedding Layer
Bibliography
Index
End User License Agreement

Content preview from Machine Learning and AI with Simple Python and Matlab Scripts

Appendix DBack Propagation Through Time in an RNN

D.1 Back Propagation in an RNN

In this appendix, we present expressions for computing the partial derivatives of loss with respect to RNN parameters of and during the back propagation through time used in RNNs as discussed in Chapter 10. Let us first present the definitions of RNN parameters from Chapter 10:

(D.1) $h Subscript t Baseline equals normal upper Theta Subscript h Baseline left-parenthesis upper W h Subscript t minus 1 Baseline plus upper U x Subscript t Baseline plus b right-parenthesis$

(D.2) $normal upper Omega Subscript t Baseline equals upper V h Subscript t Baseline plus c$

(D.3) $modifying above y with caret Subscript t Baseline equals normal upper Theta Subscript modifying above y with caret Baseline left-parenthesis normal upper Omega Subscript t Baseline right-parenthesis$

(D.4) $upper L Subscript t Baseline equals minus sigma-summation Underscript i equals 1 Overscript StartAbsoluteValue script upper I EndAbsoluteValue Endscripts y Subscript t left-parenthesis i right-parenthesis Superscript o Baseline l n left-parenthesis modifying above y with caret Subscript t left-parenthesis i right-parenthesis Baseline right-parenthesis comma$

where is realized as tanh and as softmax. In order to minimize the loss , its gradients with respect to and must be computed. Recall from Eq. (10.7) in Chapter 10 that cross‐entropy loss is defined as ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Machine Learning with Python Cookbook, 2nd Edition

Publisher Resources

ISBN: 9781394294954

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Machine Learning and AI with Simple Python and Matlab Scripts

by M. Umit Uyar

Appendix DBack Propagation Through Time in an RNN

D.1 Back Propagation in an RNN

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.