Courses

Neural Networks & Applications

General

Course Contents

The taught modules concern:
• Basic concepts
• Artificial Neural Networks
• Perceptron and ADALINE networks
• The Multi-Layer Perceptron Network and the Back-Propagation Rule
• Self-Organized Map Networks (SOM)
• Radial Base Function Networks (RBF)
• Hebian learning models
• Implementing Neural Networks in Matlab and other Software
• Learning and Generalization
• Deep Learning
• Applications of Artificial Neural Networks

Educational Goals

• introduce the student to the concept of Artificial Neural Networks and Machine Learning which is their main field of application.
• know their different types, their structure and applications, as well as their performance limits.
• Be able to use Neural Network simulation software and create applications.

General Skills

Search for, analysis and synthesis of data and information, with the use of the necessary technology
Working independently
Team work
Project planning and management
Production of new research ideas

Teaching Methods

Lectures, Exercises, Online guidance, Projected Presentations, E-mail communication, Online Synchronous and Asynchronous Teaching Platform (moodle).

Students Evaluation

Project 100%

Recommended Bibliography

Neural Networks & Machine Learning. Haykin, Simon. Papasotiriou Editions, ISBN13: 9789607182647
Neural Network Design. Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale, Orlando De Jesús. ISBN13: 9780971732117.
https://hagan.okstate.edu/NNDesign.pdf
Artificial Neural Networks. Konstantinos Diamantaras. Klidarithmos Editions, ISBN : 978-960-461-080-8
Neural Network Toolbox (Matlab). Mark Hudson Beale, Martin T. Hagan, Howard B. Demuth.