Pattern recognition in bistable networks

---

Copy For Citation

Chinarov V., Halici U., Leblebicioglu K.

Proceedings of SPIE - The International Society for Optical Engineering, vol.3722, pp.457-463, 1999 (SCI-Expanded)

• Publication Type: Article / Article
• Volume: 3722
• Publication Date: 1999
• Doi Number: 10.1117/12.342903
• Journal Name: Proceedings of SPIE - The International Society for Optical Engineering
• Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
• Page Numbers: pp.457-463
• Middle East Technical University Affiliated: Yes

Abstract

Present study concerns the problem of learning, pattern recognition and computational abilities of a homogeneous network composed from coupled bistable units. An efficient learning algorithm is developed. New possibilities for pattern recognition may be realized due to the developed technique that permits a reconstruction of a dynamical system using the distributions of its attractors. In both cases the updating procedure for the coupling matrix uses the minimization of least-mean-square errors between the applied and desired patterns.