We investigate the network complexity of multi-layered perceptrons for solving exactly a given problem. We limit our study to the class of combinatorial optimization problems. It is shown how these problems can be reformulated as binary classification problems and how they can be solved by multi-layered perceptrons. Keywords: Combinatorial Optimization, Classification, Complexity, Exact Network Configurations, Multi-Layered Perceptrons, Neural Networks.
|Place of Publication||Eindhoven|
|Publisher||Technische Universiteit Eindhoven|
|Publication status||Published - 1991|