Sample complexity bounds for recurrent neural networks with application to combinatorial graph problems
Learning to predict solutions to real-valued combinatorial graph problems promises efficient
approximations. As demonstrated based on the NP-hard edge clique cover number …
approximations. As demonstrated based on the NP-hard edge clique cover number …
Using continuous Hopfield neural network for solving a new optimization architecture model of probabilistic self organizing map
N Joudar, Z En-Naimani, M Ettaouil - Neurocomputing, 2019 - Elsevier
Probabilistic models have proven their strength to model many natural phenomena as close
as possible to reality, in particular, the probabilistic self organizing map (PRSOM) that …
as possible to reality, in particular, the probabilistic self organizing map (PRSOM) that …
[图书][B] The application of the self organizing map to the vehicle routing problem
M Steinhaus - 2015 - search.proquest.com
Abstract The Vehicle Routing Problem (VRP) is an NP-hard, combinatorial optimization
problem. For NP-hard problems, there is no known polynomial time algorithm to solve these …
problem. For NP-hard problems, there is no known polynomial time algorithm to solve these …
Modified self organizing neural network algorithm for solving the Vehicle Routing Problem
M Steinhaus, AN Shirazi… - 2015 IEEE 18th …, 2015 - ieeexplore.ieee.org
Although a significant amount of research has focused on the use of Artificial Neural
Networks (ANNs) for solving the Traveling Salesman Problem (TSP), there is considerably …
Networks (ANNs) for solving the Traveling Salesman Problem (TSP), there is considerably …
Correntropy in data classification
In this chapter, the usability of the correntropy-based similarity measure in the paradigm of
statistical data classification is addressed. The basic theme of the chapter is to compare the …
statistical data classification is addressed. The basic theme of the chapter is to compare the …
Finding quasi core with simulated stacked neural networks
M Bhattacharyya, S Bandyopadhyay - Information Sciences, 2015 - Elsevier
Studying networks is promising for diverse applications. We are often interested in exploring
significant substructures in different types of real-life networks. Finding cliques, which denote …
significant substructures in different types of real-life networks. Finding cliques, which denote …
Artificial intelligence-based techniques for operations research and optimization
KV Seetharam - Applied Intelligence in Human-Computer …, 2023 - taylorfrancis.com
Operations research and optimization (OR&O) problems involve obtaining the best set of
decisions, among several options, for maximizing a certain benefit or minimizing a certain …
decisions, among several options, for maximizing a certain benefit or minimizing a certain …
Providing efficient certification services against active attacks in ad hoc networks
Most of previous research work in key management can only resist passive attacks, such as
dropping the certificate request, and are vulnerable under active attacks, such as returning a …
dropping the certificate request, and are vulnerable under active attacks, such as returning a …
Stability and parameters estimation in dynamical systems of type recur-rent networks, contributions to new non-linear optimization models: applications to real …
N Joudar - 2018 - toubkal.imist.ma
Grâce à la solidité de ses bases théoriques et à la robustesse de ses algorithmes, les
réseaux de neurones récurrents sont devenus l'alternative la plus privilégiée pour la …
réseaux de neurones récurrents sont devenus l'alternative la plus privilégiée pour la …