Course Content
Biological memory mechanisms. Neural basis for human memory. Neuron models. The classification problem. Linear Classifiers. Training learning and generalization. Perception convergence theorem. Ho-Kashyap algorithm. Multilayer feed forward networks. Number of hidden nodes and VC-dimension. Kolmogorov"s theorem on representation of functions of several variables. The back propagation algorithms. Other algorithms. Applications. Hopfield network. Generalized convergence theorem. Computational power and capacity. Applications. Cellular neural networks. Stability. Convergence and computational power. Applications. Kohonen"s algorithm for self organizing networks. Convergence proof. Applications. Grossberg"s algorithm. Adaptive resonance theory (ART) for binary and analog input patterns. Simulated Annealing and Boltzmann machines. Principles of statistical neuro dynamics. Deductive theory of learning. Valiant"s model. Learnability and VC-dimension.
Text / References
- 1 Minsky M.L. and Papert S.: `Perceptrons", MIT Press, 1988. Gonzalez and Tou: `Pattern Recognition Principles`, Addison Wesley, 1974. Mc Clelland J.L. and Rumelhart O.E. ed.:`parallel distributed processing : Explorations in microstructure of cognition", MIT Press, 1986. Aarts E. and Korst J.:`Simulated Annealing and Boltzmann machines", John Wiley, 1989. Kohonen T.: `Self organization and Associative memory", Springer Verlag, 1984.