Introduction (Basic artificial neuron models, Activation functions, Basic Neural Networks’ structures). Basic algorithms of learning process (Basic learning paradigms and the statistical nature of the learning process). Basic concepts of the Learning Theory. Perceptron algorithm (algorithm foundation, convergence theorem and performance measure). Mean square Error algorithm (Wiener-Hopf equations, solution based on steepest descent algorithm, convergence study, learning curve and learning method of the ADALINE element. Multi Layer Perceptrons (MLPs). The Back Propagation (BP) algorithm. The Generalized Delta Rule. Learningmodes and implementation aspects. Introduction to Hopfield and Kohonen Networks.
Introduction to Genetic / Evolutionary Algorithms G/E A (Introduction, What is a GA, biological background, design of a GA, chromosomes’ representation, selection operators, crossover nad mutation operators, GA’s parameters). Theoretical foundation of Genetic Algorithms (Introduction, Who will live and who will die: The Basic Theorem (Schema Theorem). Why and How GAs operate. Computer implementation of a GA (Introduction, Data Structures, Reproduction, Crossover and Mutation. The main program (coding, constrains). Applications to Engineering and Technology. Evolutionary NNs.