Backpropagation and Ordered Derivatives in the Time Scales Calculus
Abstract
Backpropagation is the most widely used neural network learning technique. It is based on the mathematical notion of an ordered derivative. In this paper, we present a formulation of ordered derivatives and the backpropagation training algorithm using the important emerging area of mathematics known as the time scales calculus. This calculus, with its potential for application to a wide variety of inter-disciplinary problems, is becoming a key area of mathematics. It is capable of unifying continuous and discrete analysis within one coherent theoretical framework. Using this calculus, we present here a generalization of backpropagation which is appropriate for cases beyond the specifically continuous or discrete. We develop a new multivariate chain rule of this calculus, define ordered derivatives on time scales, prove a key theorem about them, and derive the backpropagation weight update equations for a feedforward multilayer neural network architecture. By drawing together the time scales calculus and the area of neural network learning, we present the first connection of two major fields of research.
Recommended Citation
J. E. Seiffertt and D. C. Wunsch, "Backpropagation and Ordered Derivatives in the Time Scales Calculus," IEEE Transactions on Neural Networks, vol. 21, no. 8, pp. 1262 - 1269, Institute of Electrical and Electronics Engineers (IEEE), Jan 2010.
The definitive version is available at https://doi.org/10.1109/TNN.2010.2050332
Department(s)
Electrical and Computer Engineering
International Standard Serial Number (ISSN)
1045-9227
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2010 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 Jan 2010
