Extension of theory and methodology for using multilayer perceptrons and error correction learning. More about learning theory and support vector machines (SVM). Basics about statistical methodology for learning systems and techniques based on “mixture of experts”. Use of attractor neural networks and SOM (Self-Organizing Maps) as associative memory and for clustering. Distributed and localized representation in neural networks, e.g. fuzzy representation and Gaussian mixtures. ANN for time series prediction. Development trends in brain-inspired algorithms and architectures.
A project where ANN is applied in practice on some larger problem involving classification, prediction, categorization, clustering and/or visualization.