Artificial Neural Network Theory

Course description

The basic principles of neural networks and soft computing are presented in terms of their properties, types, advantages and disadvantages. Biological neurons and nervous systems are discussed, together with several neural models, single-layer and multilayer networks, feedforward and feedback networks, and associative memory. Supervised and unsupervised learning methods are explained, such as delta, backpropagation, competitive, Hebbian, content-addressable, reinforcement and recurrent learning. Activation (transfer) functions are explained for many network types, such as radial basis and wavelet networks, as well as adaptive resonance theory. Examples of neural network applications are given.

The basic concepts of neural networks and soft computing in terms of characterization, categorization, advantages and disadvantages are introduced. Biological neurons and nervous systems are overviewed. Various models of neural such as single and multi layer networks, feed forward and feedback networks, associative memories are explained. Then, the learning rules (supervised and unsupervised) are described such as delta, back propagation, competitive, Hebbian, content addressable, reinforcement recurrent learning rule. Activation functions (transfer functions) are then explained in various models of networks for example radial basis function, wavelet function including adaptive resonance theory. Some neural applications are exemplified.