loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: B. V. Kryzhanovsky ; V. M. Kryzhanovsky and A. L. Mikaelian

Affiliation: Center of Optical Neural Technologies, SR Institute of System Analisys RAS, Russian Federation

Keyword(s): Binary optimization, neural networks, local minimum.

Related Ontology Subjects/Areas/Topics: Informatics in Control, Automation and Robotics ; Intelligent Control Systems and Optimization ; Optimization Algorithms

Abstract: The standard method in optimization problems consists in a random search of the global minimum: a neuron network relaxes in the nearest local minimum from some randomly chosen initial configuration. This procedure is to be repeated many times in order to find as deep an energy minimum as possible. However the question about the reasonable number of such random starts and whether the result of the search can be treated as successful remains always open. In this paper by analyzing the generalized Hopfield model we obtain expressions describing the relationship between the depth of a local minimum and the size of the basin of attraction. Based on this, we present the probability of finding a local minimum as a function of the depth of the minimum. Such a relation can be used in optimization applications: it allows one, basing on a series of already found minima, to estimate the probability of finding a deeper minimum, and to decide in favor of or against further running the program. The theory is in a good agreement with experimental results. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.228.168.200

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
V. Kryzhanovsky, B.; M. Kryzhanovsky, V. and L. Mikaelian, A. (2007). BINARY OPTIMIZATION: A RELATION BETWEEN THE DEPTH OF A LOCAL MINIMUM AND THE PROBABILITY OF ITS DETECTION. In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-972-8865-82-5; ISSN 2184-2809, SciTePress, pages 5-10. DOI: 10.5220/0001621000050010

@conference{icinco07,
author={B. {V. Kryzhanovsky}. and V. {M. Kryzhanovsky}. and A. {L. Mikaelian}.},
title={BINARY OPTIMIZATION: A RELATION BETWEEN THE DEPTH OF A LOCAL MINIMUM AND THE PROBABILITY OF ITS DETECTION},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2007},
pages={5-10},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001621000050010},
isbn={978-972-8865-82-5},
issn={2184-2809},
}

TY - CONF

JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - BINARY OPTIMIZATION: A RELATION BETWEEN THE DEPTH OF A LOCAL MINIMUM AND THE PROBABILITY OF ITS DETECTION
SN - 978-972-8865-82-5
IS - 2184-2809
AU - V. Kryzhanovsky, B.
AU - M. Kryzhanovsky, V.
AU - L. Mikaelian, A.
PY - 2007
SP - 5
EP - 10
DO - 10.5220/0001621000050010
PB - SciTePress