Law Discovery using Neural Networks

Saito, Kazumi; Nakano, Ryohei

Law Discovery using Neural Networks

Download BibTeX Cite

Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Neural Networks. Pages 1078-1082.

Abstract

This paper proposes a new connectionist approach to numeric law discovery; i.e., neural networks (law-candidates) are trained by using a newly invented second-order learning algorithm based on a quasi-Newton method, called BPQ, and the Minimum Description Length criterion selects the most suitable from lawcandidates. The main advantage of our method over previous work of symbolic or connectionist approach is that it can efficiently discover numeric laws whose power values are not restricted to integers. Experiments showed that the proposed method works well in discovering such laws even from data containing irrelevant variables or a small amount of noise.

Kazumi Saito, and Ryohei Nakano. 1997. Law Discovery using Neural Networks. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97. IJCAI, 1078–1082. https://ijcai.org/proceedings/1997/156

@inproceedings{ijcai1997p156,
  title     = {Law Discovery using Neural Networks},
  author    = {Saito, Kazumi and Nakano, Ryohei},
  booktitle = {Proceedings of the Fifteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-97}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Martha E. Pollack},
  pages     = {1078--1082},
  year      = {1997},
  note      = {Neural Networks},
  url       = {https://ijcai.org/proceedings/1997/156},
}

TY  - CPAPER
TI  - Law Discovery using Neural Networks
AU  - Saito, Kazumi
AU  - Nakano, Ryohei
T2  - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1997
SP  - 1078
EP  - 1082
UR  - https://ijcai.org/proceedings/1997/156
ER  -