DocumentCode
1909367
Title
Backpropagation for linearly-separable patterns: A detailed analysis
Author
Rasconi, Paolo F. ; Gori, Marco ; Tesi, Albert0
Author_Institution
Dipartimento di Sistemi e Inf., Florence Univ., Italy
fYear
1993
fDate
1993
Firstpage
1818
Abstract
A sufficient condition for learning without local minima in multilayered networks is proposed. A fundamental assumption on the network architecture is removed. It is proved that the conclusions drawn by M. Gori and A. Tesi (IEEE Trans. Pattern Anal. Mach. Intell., vol.14, no.1, pp.76-86, (1992)) also hold provided that the weight matrix associated with the hidden and output layer is pyramidal and has full rank. The analysis is carried out by using least mean squares (LMS)-threshold cost functions, which allow the identification of spurious and structural local minima
Keywords
backpropagation; feedforward neural nets; matrix algebra; backpropagation; learning; least mean squares; local minima; multilayered networks; neural nets; sufficient condition; threshold cost functions; weight matrix; Algorithm design and analysis; Backpropagation algorithms; Cost function; Electronic mail; Interpolation; Joining processes; Neurons; Pattern analysis; Shape; Sufficient conditions;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993., IEEE International Conference on
Conference_Location
San Francisco, CA
Print_ISBN
0-7803-0999-5
Type
conf
DOI
10.1109/ICNN.1993.298833
Filename
298833
Link To Document