Combining Genetic Algorithms
and Neural Networks

1994, English, 100+ pages, postscript, .ps.gz, code (.tar.gz)
Master Thesis at the University of Tennessee at Knoxville, USA.

Neural networks and genetic algorithms demonstrate powerful problem solving ability. They are based on quite simple priciples, but take advantage of their mathematical nature: non-linear iteration.
Neural Networks with backpropagation learning showed results by searching various kinds of functions. However, the choice of the basic parmeter (network topology, learning rate, initial weights) often already determines the success of the training process. The selection of these parameter follow in practical use rules of thumb, but their value is at most arguable.
Genetic algorithms are global search methods that are based on principles like selection, crossover and mutation. This thesis examines how genetic algorihtms can be used to opimize the network topology etc. of neural networks. It investigates, how various encoding strategies influence the GANN synergy. They are evaluated according to their performance on academic and practical problems of different complexity.
A research tool has been implemented, using the programming language C++. Its basic properties are described.