Design of Neural Networks

The paper offers a critical analysis of the procedure observed in many applications of neural networks. Given a problem to be solved, a favorite NN-architecture is chosen and its parameters tuned with some standard training algorithm, but without taking in consideration relevant features of the problem or possibly its interdisciplinary nature. Three relevant benchmark problems are discussed to illustrate the thesis that “brute force solving is not the same as understanding”. Keywords. Neural networks, pre-processing, problem-oriented design

• Type: Conference
• Year: 2007
• Where: KES
• Authors: Claudio Moraga
• Keywords: Consideration Relevant Features, KES 2007, Neural Networks, Relevant Benchmark Problems