Offered: Fall 2025 (current)
An extensive course on neural network architectures and learning algorithms with theory and applications. Temporal and optimal linear associative memories, fuzzy control. Cohen-Grossberg theorem. Unsupervised learning. Higher-order competitive, differential Hebbian learning networks. Supervised learning. Adaptive estimation and stochastic approximation. Adaptive vector quantization, mean-square approach. Kohonen self-organizing maps. Grossberg theory. Simulated annealing. Boltzman and Cauchy learning. Adaptive resonance. Gabor functions and networks, Recurrent neural network, Long Short Term Memory, Gated Recurrent Unit, Convolution Neural Network, Generative Adversarial Network, Transformer, Bert, Fuzzy metrics, Fuzzification, Defuzzification methods, Representations of Fuzzy world, Neuro Fuzzy methods.
The core objectives of this course are:
introduce the neural networks for classification and regression;
introduce fuzzy systems to solve problems using control by mapped in fuzzy world;
to give design methodologies for neural networks & fuzzy systems ;
to provide knowledge upon neural network & fuzzy systems tuning and optimization;
to demonstrate different neural network & fuzzy systems design policies;
1. To Be Added
| # | Description | Weight | Edit |
|---|
