Improvement of associative memory by means of inductive learning

Tomohiro Takagi, Hirohide Ushida, Atsushi Imura, Toru Yamaguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Artificial neural networks acquire their average knowledge by learning a huge number of instances. However, in the real world, there are many instances which can not be generalized by such a learning method. The neural network constructed by the conventional learning method is not able to recognize a new instance, which is against the average knowledge. On the other hand, inductive learning in an artificial intelligence constructs knowledge representing the new instance as an exceptional knowledge and can recognize it well. In this paper, we firstly show that the correct recognition ratio increases as the number of training data increases. Next, we attempt the improvement of associative memory by constructing an exceptional instance knowledge when an unknown instance is given. We apply the proposed method to facial expressions recognition in order to confirm the advantage of it.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages2607-2610
Number of pages4
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1 Dec 1993
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 25 Oct 199329 Oct 1993

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume3

Conference

ConferenceProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period25/10/9329/10/93

Fingerprint Dive into the research topics of 'Improvement of associative memory by means of inductive learning'. Together they form a unique fingerprint.

  • Cite this

    Takagi, T., Ushida, H., Imura, A., & Yamaguchi, T. (1993). Improvement of associative memory by means of inductive learning. In Proceedings of the International Joint Conference on Neural Networks (pp. 2607-2610). (Proceedings of the International Joint Conference on Neural Networks; Vol. 3). Publ by IEEE.