Neural Networks

The course introduces the theory and practice of neural computation. It provides the principles of neurocomputing with artificial neural networks widely used for addressing real-world problems such as classification, regression, system identification, pattern recognition, data mining, time-series prediction, etc. Artificial neural network models are inspired by biological neural networks. The course begins with an overview of information processing principles in biological systems. The core of the course consists of the theory and properties of major neural network algorithms and architectures. Two main topics are covered: learning linear models by perceptrons, and learning non-linear models by probabilistic neural networks, multilayer perceptrons, radial-basis function networks, and Kohonen neural networks.

 

Giorgos Papadourakis received his B.S. degree from the Michigan Technological University, his Master’s degree from the University of Cincinnati, and his Ph.D. degree from the University of Florida, all in Electrical Engineering. Currently he is the director of the MSc program “Informatics Engineering” at Technological Educational Institute of Crete.

 

Dr. Papadourakis’s research interests include Intelligent System applications, firmware and software development, Cyber Security, Engineering Education, and Open Distance Learning. He has authored (editor) of 17 books, over 36 Journal and 172 International Conference publications. He has coordinated or participated in over 102 National, European and International projects. He has been Conference Chair in 15 International Conferences. He has been a member of several program committees of international Conferences and reviewer of several international conferences, Journals and agencies.