19 August 1993 Design techniques for the control of errors in backpropagation neural networks
Author Affiliations +
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.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Daniel C. St. Clair, Daniel C. St. Clair, Gerald E. Peterson, Gerald E. Peterson, Stephen Aylward, Stephen Aylward, William E. Bond, William E. Bond, } "Design techniques for the control of errors in backpropagation neural networks", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152636; https://doi.org/10.1117/12.152636
PROCEEDINGS
12 PAGES


SHARE
Back to Top