A pattern recognition approach to understanding the multi-layer perceptron
作者： Ian D. Longstaff , John F. Cross
DOI: 10.1016/0167-8655(87)90072-9
关键词: Backpropagation 、 Perceptron 、 Pattern recognition (psychology) 、 Artificial neural network 、 Pattern recognition 、 Computer science 、 Multilayer perceptron 、 Feature vector 、 Training set 、 Representation (mathematics) 、 Artificial intelligence 、 Neutral network
摘要: Abstract This letter is concerned with the operation of a class multi-layer associative networks commonly known as perceptron (MLP), Rumelharte network or back-propagation network. We describe MLP pattern recognition device in terms feature-space representation. allows an understanding how structure training data represented internally machine.
elsevier.com
sci-hub.se 参考文章(4)
David H. Ackley, Geoffrey E. Hinton, Terrence J. Sejnowski, A learning algorithm for boltzmann machines Cognitive Science. ,vol. 9, pp. 147- 169 ,(1985) , 10.1207/S15516709COG0901_7
D. Foley, Considerations of sample and feature size IEEE Transactions on Information Theory. ,vol. 18, pp. 618- 626 ,(1972) , 10.1109/TIT.1972.1054863
D. E. Rumelhart, G. E. Hinton, R. J. Williams, Learning internal representations by error propagation Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. ,vol. 1, pp. 318- 362 ,(1986)
Peter E. Hart, Richard O. Duda, Pattern classification and scene analysis A Wiley-Interscience Publication. ,(1973)