Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Convergence properties of the softassign quadratic assignment algorithm.

A Rangarajan1, A Vuille, E Mjolsness

  • 1Department of Diagnostic Radiology, 332 BML, Yale University, School of Medicine, 333 Cedar Street, New Haven, CT 06520-8042, USA.

Neural Computation
|July 29, 1999
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Feasibility of Passive ECG Bio-sensing and EMA Emotion Reporting Technologies and Acceptability of Just-in-Time Content in a Well-being Intervention, Considerations for Scalability and Improved Uptake.

Affective science·2022
Same author

Data-Driven Discovery of Extravasation Pathway in Circulating Tumor Cells.

Scientific reports·2017
Same author

Thrombospondin-1 repression is mediated via distinct mechanisms in fibroblasts and epithelial cells.

Oncogene·2015
Same author

Thrombospondin-1 repression is mediated via distinct mechanisms in fibroblasts and epithelial cells.

Oncogene·2014
Same author

Combined in silico/in vivo analysis of mechanisms providing for root apical meristem self-organization and maintenance.

Annals of botany·2012
Same author

Introduction of SV40ER and hTERT into mammospheres generates breast cancer cells with stem cell properties.

Oncogene·2011
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

The softassign algorithm, a neural network for optimization, has demonstrated convergence properties. This finding, combined with its proven effectiveness, makes it ideal for quadratic assignment problems.

Area of Science:

  • Artificial Intelligence
  • Neural Networks
  • Optimization Algorithms

Background:

  • The softassign algorithm is a neural network model for optimization tasks.
  • Its effectiveness is established in problems like the traveling salesman problem, graph matching, and partitioning.
  • However, its convergence properties remain unstudied.

Purpose of the Study:

  • To analyze the convergence properties of the softassign quadratic assignment algorithm.
  • To provide theoretical justification for the algorithm's successful simulations.

Main Methods:

  • Construction of discrete-time Lyapunov functions.
  • Analysis for both exact and approximate doubly stochastic constraint satisfaction.

Main Results:

Related Experiment Videos

  • Demonstrated convergence of the softassign algorithm to a fixed point.
  • Theoretical proof of convergence properties.

Conclusions:

  • The softassign algorithm exhibits proven convergence properties.
  • Its combination of theoretical convergence and experimental success makes it suitable for neural quadratic assignment optimization.