Solvable Models of Artificial Neural Networks
Abstract
Solvable models of nonlinear learning machines are proposed, and learning in artificial neural networks is studied based on the theory of ordinary differential equations. A learning algorithm is con(cid:173) structed, by which the optimal parameter can be found without any recursive procedure. The solvable models enable us to analyze the reason why experimental results by the error backpropagation often contradict the statistical learning theory.
Cite
Text
Watanabe. "Solvable Models of Artificial Neural Networks." Neural Information Processing Systems, 1993.Markdown
[Watanabe. "Solvable Models of Artificial Neural Networks." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/watanabe1993neurips-solvable/)BibTeX
@inproceedings{watanabe1993neurips-solvable,
title = {{Solvable Models of Artificial Neural Networks}},
author = {Watanabe, Sumio},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {423-430},
url = {https://mlanthology.org/neurips/1993/watanabe1993neurips-solvable/}
}