Structure Evolution and Incomplete Induction

We present an application of arti cial neural networks to machine condition monitoring. Since several signal preprocessing methods produce high dimensional feature vectors there is a need for optimizing the structure of the neural network. We examine three methods for nding the structure and compare the resulting networks: fully connected networks, pruning techniques and Structure Evolution and Incomplete Induction".

• Type: Conference
• Year: 1992
• Where: PPSN
• Authors: Reinhard Lohmann
• Keywords: Cial Neural Networks, Distributed And Parallel Computing, Neural Network, PPSN 1992, Signal Preprocessing Methods