Learning Feed-Forward Multi-Nets
Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. This potential lacks popularity as, without precautions, the learning rate has to drop considerably to eliminate the occurrence of unlearning. This paper introduces extensions of the Error Back-Propagation algorithm to enable function preserving merging of neural modules at full learning rate.
KeywordsHide Neuron Modular Network Schedule Delay Modular Neural Network Neural Module
Unable to display preview. Download preview PDF.
- Macready, W.G. Siapas, A.G Kauffman, S.A.: Criticality and parallelism in combinatorial optimization, Science 271, pp. 56–59 (1996).Google Scholar
- Schuermann, B.: Applications and Perspectives of Artificial Neural Networks, VDI Berichte 1526, pp. 1–14 (2000).Google Scholar
- Spaanenburg, L.: Unlearning in feed-forward nets, this proceedingGoogle Scholar
- Sprinkhuizen-Kuyper, I.G. Boers, E.J.W.: A local minimum for the 2-3-1 XOR network, IEEE Trans. on Neural Networks 10, pp. 968–971 (1999)..Google Scholar
- TerBrugge, M.H. Nijhuis, J.A.G. Spaanenburg, L.: License-Plate Recognition, pp. 263–296, in: Jain, L.C. Lazzarini, B.: Intelligent Techniques in Character Recognition: Practical Applications: CRC Press 199Google Scholar
- VanVeelen, M. Nijhuis, J.A.G. Spaanenburg, L.: Process fault detection through quantitative analysis of learning in neural networks, Proceedings ProRISC’2000, pp. 557–565 (2000).Google Scholar
- Nijhuis, J.A.G. Siggelkow, A. Spaanenburg, L.: Delay-sensitive learning of neural networks, Digest INNC pp. 1–697 (1990).Google Scholar
- Barakova, E.I., Learning Reliability: a study on indecisiveness in sample selection, Ph.D. thesis Groningen University: Groningen 1999.Google Scholar