Tampere University of Technology

TUTCRIS Research Portal

A Primal Neural Network for Online Equality-Constrained Quadratic Programming

Research output: Contribution to journalArticleScientificpeer-review


Original languageEnglish
Pages (from-to)381–388
Number of pages8
JournalCognitive Computation
Issue number2
Publication statusPublished - 2018
Publication typeA1 Journal article-refereed


This paper aims at solving online equality-constrained quadratic programming problem, which is widely encountered in science and engineering, e.g., computer vision and pattern recognition, digital signal processing, and robotics. Recurrent neural networks such as conventional GradientNet and ZhangNet are considered as powerful solvers for such a problem in light of its high computational efficiency and capability of circuit realisation. In this paper, an improved primal recurrent neural network and its electronic implementation are proposed and analysed. Compared to the existing recurrent networks, i.e. GradientNet and ZhangNet, our network can theoretically guarantee superior global exponential convergence. 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, which also verify the effectiveness of the proposed model for online equality-constrained quadratic programming.


  • Global exponential convergence, Online equality-constrained quadratic programming, Recurrent neural networks, Robustness analysis

Publication forum classification

Field of science, Statistics Finland