On the Synthesis of Nonlinear Continuous Neural Networks

Samir Ranjan Das

doi:10.1109/21.87077

On the Synthesis of Nonlinear Continuous Neural Networks

Samir Ranjan Das

Computer Science

Research output: Contribution to journal › Letter › peer-review

14 Scopus citations

Abstract

A synthesis technique for a class of nonlinear neural networks that subsumes Hopfield's network with graded response is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested.

Original language	English
Pages (from-to)	413-418
Number of pages	6
Journal	IEEE Transactions on Systems, Man and Cybernetics
Volume	21
Issue number	2
DOIs	https://doi.org/10.1109/21.87077
State	Published - 1991

Access to Document

10.1109/21.87077

Cite this

@article{48ec8de514fb4dd295f2875c4da906e1,

title = "On the Synthesis of Nonlinear Continuous Neural Networks",

abstract = "A synthesis technique for a class of nonlinear neural networks that subsumes Hopfield's network with graded response is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested.",

author = "Das, \{Samir Ranjan\}",

year = "1991",

doi = "10.1109/21.87077",

language = "English",

volume = "21",

pages = "413--418",

journal = "IEEE Transactions on Systems, Man and Cybernetics",

issn = "0018-9472",

number = "2",

}

TY - JOUR

T1 - On the Synthesis of Nonlinear Continuous Neural Networks

AU - Das, Samir Ranjan

PY - 1991

Y1 - 1991

N2 - A synthesis technique for a class of nonlinear neural networks that subsumes Hopfield's network with graded response is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested.

AB - A synthesis technique for a class of nonlinear neural networks that subsumes Hopfield's network with graded response is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested.

UR - https://www.scopus.com/pages/publications/0026124340

U2 - 10.1109/21.87077

DO - 10.1109/21.87077

M3 - Letter

AN - SCOPUS:0026124340

SN - 0018-9472

VL - 21

SP - 413

EP - 418

JO - IEEE Transactions on Systems, Man and Cybernetics

JF - IEEE Transactions on Systems, Man and Cybernetics

IS - 2

ER -

On the Synthesis of Nonlinear Continuous Neural Networks

Abstract

Access to Document

Other files and links

Fingerprint

Cite this