Tampere University of Technology

TUTCRIS Research Portal

An Improved Recurrent Network for Online Equality-Constrained Quadratic Programming

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationAdvances in Brain Inspired Cognitive Systems
Subtitle of host publication8th International Conference, BICS 2016, Beijing, China, November 28-30, 2016, Proceedings
PublisherSpringer International Publishing
ISBN (Electronic)978-3-319-49685-6
ISBN (Print)978-3-319-49684-9
DOIs
Publication statusPublished - 2016
Publication typeA4 Article in a conference publication
EventAdvances in Brain Inspired Cognitive Systems -
Duration: 1 Jan 2000 → …

Publication series

NameLecture Notes in Computer Science
Volume10023
ISSN (Print)0302-9743

Conference

ConferenceAdvances in Brain Inspired Cognitive Systems
Period1/01/00 → …

Abstract

Encouraged by the success of conventional GradientNet and recently-proposed ZhangNet for online equality-constrained quadratic programming problem, an improved recurrent network and its electronic implementation are firstly proposed and developed in this paper. Exploited in the primal form of quadratic programming with linear equality constraints, the proposed neural model can solve the problem effectively. Moreover, compared to the existing recurrent networks, i.e., GradientNet (GN) and ZhangNet (ZN), our model can theoretically guarantee superior global exponential convergence performance. Robustness performance of our such neural model is also analysed under a large model implementation error, with the upper bound of stead-state solution error estimated. Simulation results demonstrate theoretical analysis on the proposed model for online equality-constrained quadratic programming.

Publication forum classification

Field of science, Statistics Finland