Genetic Algorithm and Variable Feed-Forward Neural Networks: Theory and application

This book focuses on the real-coded genetic algorithm and different topologies of feed-forward neural networks. Results in the following areas will be reported: (1) a real-coded genetic algorithm with new crossover and mutation operations, and its applications; (2) three different topologies of variable feed-forward neural networks, and their applications to short-term electric load forecasting and hand-written graffiti recognition. The real-coded genetic algorithm (RCGA) is one evolutionary computation technique that can tackle complex optimization problems. In this book, RCGA with new genetic operations called the average-bound crossover (ABX) and wavelet mutation (WM) will be presented. The three proposed topologies of variable feed- forward network networks are: (1) the variable- structure neural network (VSNN), (2) the variable- parameter neural network (VPNN), and (3) the variable-node-to-node-link neural network (VN2NN). By taking advantage of these networks' structures, the learning and generalization abilities of the networks can be increased. All the network parameters are tuned by the RCGA with ABX and WM.