Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

June 1, 2004, Vol. 16, No. 6, Pages 1253-1282
(doi: 10.1162/089976604773717603)
© 2004 Massachusetts Institute of Technology
Improving Generalization Capabilities of Dynamic Neural Networks
Article PDF (286.22 KB)
Abstract

This work addresses the problem of improving the generalization capabilities of continuous recurrent neural networks. The learning task is transformed into an optimal control framework in which the weights and the initial network state are treated as unknown controls. A new learning algorithm based on a variational formulation of Pontrayagin's maximum principle is proposed. Under reasonable assumptions, its convergence is discussed. Numerical examples are given that demonstrate an essential improvement of generalization capabilities after the learning process of a dynamic network.