Email this article ON THE GRADIENT OF NEURONETWORK FUNCTION
- Authors: Mishachev N.M.1, Shmyrin A.M.1
-
Affiliations:
- Lipetsk State Technical University
- Issue: Vol 22, No 3 (2017)
- Pages: 552-557
- Section: Articles
- URL: https://ogarev-online.ru/2686-9667/article/view/362842
- DOI: https://doi.org/10.20310/1810-0198-2017-22-3-552-557
- ID: 362842
Cite item
Full Text
Abstract
The paper proposes a matrix formula for the gradient of neuronetwork function ∇Wf(X;W) with respect to the parameter vector W .
About the authors
Nikolay Mikhailovich Mishachev
Lipetsk State Technical University
Email: nmish@lipetsk.ru
Candidate of Physics and Mathematics, Associate Professor of the Higher Mathematics Department Lipetsk, the Russian Federation
Anatoliy Mikhailovich Shmyrin
Lipetsk State Technical University
Email: amsh@lipetsk.ru
Doctor of Techniques, Professor, the Head of the Higher Mathematics Department Lipetsk, the Russian Federation
References
Хайкин С. С. Нейронные сети: полный курс. М.: Вильямс, 2006. Rumelhart D.E., Hinton G.E., Williams R.J. Learning Internal Representations by Error Propagation // Parallel Distributed Processing, Cambridge: MA, MIT Press. 1986. V. 1. P. 318-362.
Supplementary files
