Hash Bit Selection via Collaborative Neurodynamic Optimization With Discrete Hopfield Networks

Xinqi LI, Jun WANG, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

10 Citations (Scopus)


Hash bit selection (HBS) aims to find the most discriminative and informative hash bits from a hash pool generated by using different hashing algorithms. It is usually formulated as a binary quadratic programming problem with an information-theoretic objective function and a string-length constraint. In this article, it is equivalently reformulated in the form of a quadratic unconstrained binary optimization problem by augmenting the objective function with a penalty function. The reformulated problem is solved via collaborative neurodynamic optimization (CNO) with a population of classic discrete Hopfield networks. The two most important hyperparameters of the CNO approach are determined based on Monte Carlo test results. Experimental results on three benchmark data sets are elaborated to substantiate the superiority of the collaborative neurodynamic approach to several existing methods for HBS.
Original languageEnglish
Pages (from-to)5116-5124
Number of pages9
JournalIEEE Transactions on Neural Networks and Learning Systems
Issue number10
Early online date9 Apr 2021
Publication statusPublished - Oct 2022
Externally publishedYes


  • Collaborative neurodynamic optimization (CNO)
  • discrete Hopfield network (DHN)
  • hash bit selection (HBS)


Dive into the research topics of 'Hash Bit Selection via Collaborative Neurodynamic Optimization With Discrete Hopfield Networks'. Together they form a unique fingerprint.

Cite this