Training Recurrent Neural Networks as a Constraint Satisfaction Problem release_66op3yth75hczkxbjf5k2nbzzi

by Hamid Khodabandehlou, M. Sami Fadali

Released as a article .

2018  

Abstract

This paper presents a new approach for training artificial neural networks using techniques for solving the constraint satisfaction problem (CSP). The quotient gradient system (QGS) is a trajectory-based method for solving the CSP. This study converts the training set of a neural network into a CSP and uses the QGS to find its solutions. The QGS finds the global minimum of the optimization problem by tracking trajectories of a nonlinear dynamical system and does not stop at a local minimum of the optimization problem. Lyapunov theory is used to prove the asymptotic stability of the solutions with and without the presence of measurement errors. Numerical examples illustrate the effectiveness of the proposed methodology and compare it to a genetic algorithm and error backpropagation.
In text/plain format

Archived Files and Locations

application/pdf  881.1 kB
file_oiyvdnos7fcphcbir3q7tbfodi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-04-17
Version   v5
Language   en ?
arXiv  1803.07200v5
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: da00b846-9f9a-400d-b46e-a8fe183428e9
API URL: JSON