Neural Network and Local Search to Solve Binary CSP

Adil Bouhouch, Hamid Bennis, Chakir Loqman, Abderrahim El Qadi


Continuous Hopfield neural Network (CHN) is one of the effective approaches to solve Constrain Satisfaction Problems (CSPs). However, the main problem with CHN is that it can reach stabilisation with outputs in real values, which means an inconsistent solution or an incomplete assignment of CSP variables. In this paper, we propose a new hybrid approach combining CHN and min-conflict heuristic to mitigate these problems. The obtained results  show  an  improvement  in  terms  of  solution  quality,  either  our approach achieves feasible soluion with a high rate of convergence, furthermore, this approach can also enhance theperformance more than conventional CHN in some cases, particularly, when the network crashes.


Constraint Satisfaction Problem; Continuous Hopfield Neural Network; Meeting Scheduling; Quadratic Problem; Min-Conflict

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics