Design Techniques For The Control Of Errors In Backpropagation Neural Networks
Abstract
A significant problem in the design and construction of an artificial neural network for function approximation is limiting the magnitude and variance of errors when the network is used in the field. Network errors can occur when the training data does not faithfully represent the required function due to noise or low sampling rates, when the network's flexibility does not match the variability of the data, or when the input data to the resultant network is noisy. This paper reports on several experiments whose purpose was to rank the relative significance of these error sources and thereby find neural network design principles for limiting the magnitude and variance of network errors.
Recommended Citation
D. C. St Clair et al., "Design Techniques For The Control Of Errors In Backpropagation Neural Networks," Proceedings of SPIE - The International Society for Optical Engineering, vol. 1966, pp. 372 - 383, Society of Photo-optical Instrumentation Engineers, Aug 1993.
The definitive version is available at https://doi.org/10.1117/12.152636
Department(s)
Mathematics and Statistics
Second Department
Computer Science
International Standard Serial Number (ISSN)
1996-756X; 0277-786X
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 2023 Society of Photo-optical Instrumentation Engineers, All rights reserved.
Publication Date
19 Aug 1993
