Items list
Description
Part A covers elements of computation theory, artificial intelligence, machine learning, neural networks, fuzzy logic and evolutionary computation. It examines natural computation and computational intelligence, optimization topics in computational intelligence, theoretical foundations and problems, the no-free-lunch theorem, and different forms of optimization including combinatorial, global, local and constrained optimization. It also covers multi-objective optimization, evolutionary computation and algorithms, the genetic algorithm and its mechanisms of selection, crossover and mutation, evolutionary techniques, genetic programming, grammatical evolution, evolutionary strategies, variants of genetic and evolutionary algorithms and applications. Algorithms inspired by population social behaviour are also studied, including swarm intelligence, particle swarm optimization, initialization, convergence, exploration and exploitation, applications of particle swarm optimization, ant colony and bee colony models, memetic algorithms and differential evolution. Part B covers neural networks and neural computation, biological and artificial neurons, neuron structure and activation functions, training, generalization and learning in neural networks, supervised, unsupervised and reinforcement learning, and applications in science and technology. Topics include classification and regression, linear and nonlinear classifiers, neural networks as cost-function optimization classifiers, perceptrons and multilayer perceptrons, support vector machines, probabilistic neural networks, recurrent networks, Boltzmann machines, time-delay and radial-basis networks, vector quantization, Kohonen self-organizing maps, deep learning neural networks and applications, statistical learning theory, interpretation of neural-network outputs, classification ability and memory capacity, and selected topics in cellular automata, artificial immune systems and membrane computing.
