This course covers various aspect of neural networks, from fundamentals to advanced concepts. Topics include feed-forward neural networks, kernel-based approaches, deep learning, recurrent neural networks, Hopfield networks, Kohonen Self-Organized Maps, Grossberg Adaptive Resonance Theory, Helmholtz machines, MDL, Symbolic neural nets, and space-time neurodynamics, with links to computational neuroscience. Theoretical foundations of supervised, unsupervised, and reinforcement learning are described. Advanced machine learning implementations include image processing, speech recognition, game playing, time series prediction, and neurocontrol.
The course is self-contained, preliminary knowledge of neural networks basics is useful but not required. Students at the advanced level are expected to complete a project implementing a neural network to solve a pattern recognition task, while students at the basic level will be evaluated based on conceptual designs.