Convergence Behaviour of Connectionist Models in Large Scale Diagnostic Problems

Though artificial neural networks have been successfully applied for diagnostic problems of different natures, difficulties arise by applying this approach, especially the most frequently used back propagation (BP) procedure, for large scale technical diagnostic problems. Therefore, some acceleration techniques of the BP procedure are described and investigated in the paper. Some network models isomorphic to conventional pattern recognition techniques are also enumerated, with special emphasis on the Condensed Nearest Neighbour Network (CNNN), which is a new, self-organizing network model with supervised learning ability. The surveyed techniques are analyzed and compared on a diagnostic problem with more than 300 pattern features.

[1]  D Barschdorff,et al.  Real-time failure detection on complex mechanical structures via parallel data processing , 1986 .

[2]  Christopher Rose,et al.  Minimum distance automata in parallel networks for optimum classification , 1989, Neural Networks.

[3]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[4]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[5]  D. Barschdorff,et al.  Neuronale Netze als Signal- und Musterklassifikatoren / Neural networks as signal and pattern classifiers , 1990 .

[6]  L. Riekert,et al.  K. J. Laidler: Chemical Kinetics, Second Edition. Mc Graw Hill Book Company, New York 1965. 566 Seiten. Preis: $ 9,50 , 1966, Berichte der Bunsengesellschaft für physikalische Chemie.

[7]  László Monostori,et al.  Multiprocessor systems for connectionist diagnosis of technical processes , 1991 .

[8]  Peter Mertens,et al.  Expertensysteme in der Produktion , 1991 .

[9]  G. Mirchandani,et al.  On hidden nodes for neural nets , 1989 .

[10]  Michael T. Manry,et al.  Iterative improvement of a Gaussian classifier , 1990, Neural Networks.

[11]  László Monostori,et al.  Neural networks—Their applications and perspectives in intelligent machining , 1991 .

[12]  László Monostori,et al.  A pattern recognition based vibration monitoring module for machine tools , 1988 .

[13]  Peter E. Hart,et al.  The condensed nearest neighbor rule (Corresp.) , 1968, IEEE Trans. Inf. Theory.

[14]  László Monostori.  Learning procedures in machine tool monitoring , 1986 .

[15]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[16]  L. Monostori.  SIGNAL PROCESSING AND DECISION MAKING IN MACHINE TOOL MONITORING SYSTEMS. , 1988 .

[17]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[18]  J. Makhoul,et al.  Formation of disconnected decision regions with a single hidden layer , 1989, International 1989 Joint Conference on Neural Networks.

[19]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[20]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.