Machine learning and AI with simple Python and Matlab scripts : courseware for non-computing majors / M. eUmit Uyar.

Format:

Book

Author/Creator:

Uyar, M. eUmit, author.

Contributor:

Wiley InterScience (Online service)

Language:

English

Subjects (All):

Machine learning.

Physical Description:

1 online resource

Place of Publication:

Hoboken, New Jersey : John Wiley & Sons, Inc., [2025]

Contents:

Chapter 1 Introduction

1.1 Artificial Intelligence

1.2 A Historical Perspective

1.3 Principles of AI

1.4 Applications That Are Impossible Without AI

1.5 Organization of This Book

Chapter 2 Artificial Neural Networks

2.1 Introduction

2.2 Applications of ANNs

2.3 Components of ANNs

2.3.1 Neurons

2.3.2 Sigmoid Activation Function

2.3.3 Rectilinear Activation Function

2.3.4 Weights of Synapses

2.4 Training an ANN

2.5 Forward Propagation

2.5.1 Forward Propagation from Input to Hidden Layer

2.6 Back Propagation

2.6.1 Back Propagation for a Neuron

2.6.2 Back Propagation - from Output to Hidden Layer

2.6.3 Back Propagation - from Hidden Layer to Input

2.7 Updating Weights

2.8 ANN with Input Bias

2.9 A Simple Algorithm for ANN Training

2.10 Computational Complexity of ANN Training

2.11 Normalization of ANN Inputs and Outputs

2.12 Concluding Remarks

2.13 Exercises for Chapter 2

Chapter 3 ANNs for Optimized Prediction

3.1 Introduction

3.2 Selection of ANN Inputs

3.3 Selection of ANN Outputs

3.4 Construction of Hidden Layers

3.5 Case Study 1: Sleep-Study Example

3.5.1 Using Matrices for ANN Training

3.5.2 Forward Propagation

3.5.3 Back Propagation

3.5.4 Updating Weights

3.5.5 Forward Propagation with New Weights

3.5.6 Back Propagation with New Weights

3.5.7 Using Normalized Input and Output Values

3.5.8 Reducing Errors During Training

3.5.9 Implementation of Sleep-Study ANN in Python

3.5.10 Implementation of Sleep-Study ANN in Matlab

3.6 Case Study 2: Prediction of Bike Rentals

3.6.1 Python Script for Bike Rentals Using an ANN

3.6.2 Matlab Script for Bike Rentals Using an ANN.

3.7 Concluding Remarks

3.8 Exercises for Chapter 3

Chapter 4 ANNs for Financial Stock Trading

4.1 Introduction

4.2 Programs that Buy and Sell Stocks

4.3 Technical Indicators

4.3.1 Simple Moving Average

4.3.2 Momentum

4.3.3 Exponential Moving Average

4.3.4 Bollinger Bands

4.4 A Simple Algorithmic Trading Policy

4.5 A Simple ANN for Algorithmic Stock Trading

4.5.1 ANN Inputs and Outputs

4.5.2 ANN Architecture

4.6 Python Script for Stock Trading Using an ANN

4.7 Matlab Script for Stock Trading Using an ANN

4.8 Concluding Remarks

4.9 Exercises for Chapter 4

Chapter 5 ANNs for Alzheimer's Disease Prognosis

5.1 Introduction

5.2 Alzheimer's Disease

5.3 A Simple ANN for AD Prognosis

5.4 Python Script for AD Prognosis Using an ANN

5.5 Matlab Script for AD Prognosis Using an ANN

5.6 Concluding Remarks

5.7 Exercises for Chapter 5

Chapter 6 ANNs for Natural Language Processing

6.1 Introduction

6.2 Impact of Text Messages on Stock Markets

6.3 A Simple ANN for NLP

6.3.1 ANN Inputs and Outputs

6.3.2 Keywords

6.3.3 Formation of Training Data

6.3.4 ANN Architecture

6.4 Python Script for NLP Using an ANN

6.5 Matlab Script for NLP Using an ANN

6.6 Concluding Remarks

6.7 Exercises for Chapter 6

Chapter 7 Convolutional Neural Networks

7.1 Introduction

7.1.1 Training CNNs

7.2 Variations of CNNs

7.3 Applications of CNNs

7.4 CNN Components

7.5 A Numerical Example of a CNN

7.6 Computational Cost of CNN Training

7.7 Concluding Remarks

7.8 Exercises for Chapter 7

Chapter 8 CNNs for Optical Character Recognition

8.1 Introduction

8.2 A Simple CNN for OCR

8.3 Organization of Training and Reference Files

8.4 Python Script for OCR Using a CNN

8.5 Matlab Script for OCR Using a CNN

8.6 Concluding Remarks.

8.7 Exercises for Chapter 8

Chapter 9 CNNs for Speech Recognition

9.1 Introduction

9.2 A Simple CNN for Speech Recognition

9.3 Organization of Training and Reference Files

9.4 Python Script for Speech Recognition Using a CNN

9.5 Matlab Script for Speech Recognition Using a CNN

9.6 Concluding Remarks

9.7 Exercises for Chapter 9

Chapter 10 Recurrent Neural Networks

10.1 Introduction

10.2 One-to-One Single RNN Cell

10.2.1 A Simple Alphabet and One-Hot Encoding

10.2.2 Forward and Back Propagation

10.3 A Numerical Example

10.4 Multiple Hidden Layers

10.5 Embedding Layer

10.5.1 Forward and Back Propagation with Embedding

10.5.2 A Numerical Example with Embedding

10.6 Concluding Remarks

10.7 Exercises for Chapter 10

Chapter 11 RNNs for Chatbot Implementation

11.1 Introduction

11.2 Many-to-Many RNN Architecture

11.3 A Simple Chatbot

11.4 Python Script for a Chatbot Using an RNN

11.5 Matlab Script for a Chatbot Using an RNN

11.6 Concluding Remarks

11.7 Exercises for Chapter

Chapter 12 RNNs with Attention

12.1 Introduction

12.2 One-to-One RNN Cell with Attention

12.3 Forward and Back Propagation

12.4 A Numerical Example

12.5 Embedding Layer

12.6 A Numerical Example with Embedding

12.7 Concluding Remarks

12.8 Exercises for Chapter

Chapter 13 RNNs with Attention for Machine Translation

13.1 Introduction

13.2 Many-to-Many Architecture

13.3 Python Script for Machine Translation by an RNN-Att

13.4 Matlab Script for Machine Translation by an RNN-Att

13.5 Concluding Remarks

13.6 Exercises for Chapter

Chapter 14 Genetic Algorithms

14.1 Introduction

14.2 Genetic Algorithm Elements

14.3 A Simple Algorithm for a GA

14.4 An Example of a GA

14.5 Convergence in GAs

14.6 Concluding Remarks

14.7 Exercises for Chapter.

Chapter 15 GAs for Dietary Menu Selection

15.1 Introduction

15.2 Definition of the KP

15.3 A Simple Algorithm for the KP

15.4 Variations of the KP

15.5 GAs for KP Solution

15.6 Python Script for Dietary Menu Selection Using a GA

15.7 Matlab Script for Dietary Menu Selection Using a GA

15.8 Concluding Remarks

15.9 Exercises for Chapter 15

Chapter 16 GAs for Drone Flight Control

16.1 Introduction

16.2 UAV Swarms

16.3 UAV Flight Control

16.4 A Simple GA for UAV Flight Control

16.4.1 Virtual Force-Based Fitness Function

16.4.2 FGA Progression

16.4.3 Chromosome for FGA

16.5 Python Script for UAV Flight Control Using a GA

16.6 Matlab Script for UAV Flight Control Using a GA

16.7 Concluding Remarks

16.8 Exercises for Chapter

Chapter 17 GAs for Route Optimization

17.1 Introduction

17.2 Definition of the TSP

17.3 A Simple Algorithm for the TSP

17.4 Variations of the TSP

17.5 GA Solution for the TSP

17.6 Python Script for Route Optimization Using a GA

17.7 Matlab Script for Route Optimization Using a GA

17.8 Concluding Remarks

17.9 Exercises for Chapter

Chapter 18 Evolutionary Methods

18.1 Introduction

18.2 Particle Swarm Optimization

18.2.1 Applications of PSO

18.2.2 PSO Operation

18.2.3 Remarks for PSO

18.3 Differential Evolution

18.3.1 Different Versions of DE

18.3.2 Applications of DE

18.3.3 A Simple Algorithm for DE

18.3.4 Numerical Example: Maximum of sinc by DE

18.3.5 Remarks for DE

18.4 Grammatical Evolution

18.4.1 A Simple Algorithm for GE

18.4.2 Definition of GE

18.4.3 A Simple GA to Implement GE

18.4.4 Remarks on GE

Appendix A ANNs with Bias

A.1 Introduction

A.2 Training with Bias Input

A.3 Forward Propagation

A.3.1 Forward Propagation from Input to Hidden Layer.

A.3.2 Neuron Back Propagation with Bias Input

Appendix B Sleep Study ANN with Bias

B.1 Inclusion of Bias Term in ANN

B.1.1 Inclusion of Bias in Matrices

B.1.2 Forward Propagation with Biases

Appendix C Back Propagation in a CNN

Appendix D Back Propagation Through Time in an RNN

D.1 Back Propagation in an RNN

D.2 Embedding Layer

Appendix E Back Propagation Through Time in an RNN with Attention

E.1 Back Propagation in an RNN-Att

E.2 Embedding Lay.

Notes:

Electronic reproduction. Hoboken, N.J. Available via World Wide Web.

Description based on online resource; title from digital title page (viewed on March 21, 2025).

Includes bibliographical references and index.

Other Format:

Print version :

ISBN:

9781394294985

1394294980

9781394294978

1394294972

Publisher Number:

90103819556

CIPO000216531

Access Restriction:

Restricted for use by site license.