Article
Backpropagation of Accuracy
Proceedings of the International Conference on Neural Networks,1997
Abstract
We solve the problem: how to determine maximal allowable errors, possible for signals and parameters of each element of a network, proceeding from the condition that the vector of output signals of the network should be calculated with given accuracy? "Backpropagation of accuracy" is developed to solve this problem
Meeting Name
International Conference on Neural Networks,1997
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
- Backpropagation,
- Backpropagation of Accuracy,
- Maximal Allowable Errors,
- Neural Nets,
- Output Signals,
- Vector
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1997 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
1-1-1997
Publication Date
01 Jan 1997
Disciplines
Citation Information
Donald C. Wunsch, M. Yu Senashova and Alexander N. Gorban. "Backpropagation of Accuracy" Proceedings of the International Conference on Neural Networks,1997 (1997) Available at: http://works.bepress.com/donald-wunsch/159/