Manual for the implementation of neural networks in MATLAB

Inhaltsverzeichnis (Table of Contents)

• Summary
• Table of contents
• List of figures and tables
• 1. Introduction
• 2. Neural Networks
• 2.1. What are neural networks?
• 2.2 Biological background
• 2.3 General structure of neural networks
• 2.4 Properties of neural networks....
• 2.5 Learning in neural networks and weighting
• 2.6 Historical overview.....
• 2.7 Different networks models
• 2.7.1 Single-layer feed-forward networks.
• 2.7.2 Multi-layer feed-forward networks..
• 2.7.3 Recurrent networks.
• 3. MATLAB
• 3.1 General overview.
• 3.2. MATLAB
• 3.3 Matrixes in MATLAB
• 4. Realization of neural networks in MATLAB
• 4.1 Creation of neural networks with the Network/Data Manager.
• 4.2 Import of data ..
• 4.3 The implementation of an ADALINE network.
• 4.4 The implementation of a back-propagation network..
• 4.5 Self-optimizing neural networks
• 4.6 Hopfield network.
• 4.7 Summary..
• 5. Conclusion.
• 6. Table of sources.
• Books ......
• Scripts and other sources.
• Internet sources with data and time of accession
• 7. Table of abbreviations of networks

Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)

This bachelor thesis aims to provide a comprehensive manual for implementing neural networks in the MATLAB software environment. It is designed to be a resource for students in the "Master Course of Computer Studies" at the University of Applied Sciences Zittau/Görlitz.

• Theoretical background of neural networks and MATLAB
• Practical implementation of neural networks in MATLAB
• Different types of neural network architectures and their applications
• Use of MATLAB tools and functions for neural network development
• Examples and case studies to illustrate the concepts

Zusammenfassung der Kapitel (Chapter Summaries)

• Chapter 1: Introduction: This chapter provides a general introduction to the topic of neural networks and their relevance in computer science. It outlines the scope and structure of the thesis, highlighting its focus on practical implementation in MATLAB.
• Chapter 2: Neural Networks: This chapter delves into the theoretical foundations of neural networks. It covers various aspects, including the biological inspiration behind neural networks, their general structure and properties, learning algorithms, and historical development. It also explores different network models, such as single-layer feed-forward networks, multi-layer feed-forward networks, and recurrent networks.
• Chapter 3: MATLAB: This chapter focuses on the MATLAB software environment, providing a general overview of its features, functionality, and application in the context of neural network development. It explains how to work with matrices, a fundamental aspect of MATLAB programming, and introduces the various tools and functions relevant to neural networks.
• Chapter 4: Realization of Neural Networks in MATLAB: This chapter is the core of the thesis, detailing the practical implementation of neural networks in MATLAB. It covers various aspects, such as creating neural networks using the Network/Data Manager, importing data, implementing specific network types like ADALINE and back-propagation networks, and exploring self-optimizing networks and Hopfield networks. Examples and case studies are presented to demonstrate the practical application of the concepts.

Schlüsselwörter (Keywords)

This manual focuses on the implementation of neural networks in the MATLAB environment. Key terms and concepts include neural network architecture, learning algorithms, feed-forward networks, back-propagation, ADALINE, Hopfield network, MATLAB tools and functions, and practical implementation.