Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm

By S. Mirjalili, Siti Zaiton Mohd Hashim, Hossein Moradian Sardroudi. Applied Mathematics and Computation, 2012

509 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/547c9423a9c09094d2a85886b582bc41e4bb68ed

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Biogeography-based optimisation with chaos (2014, unknown): “…optimisation with chaos, Neural Computing and Applications, Vol. 25, pp. 1077 - 1097, 2014, Springer DOI: http://dx.doi.org/10.1007/s00521-014-1597-x The exploration phase occurs when an algorithm tries to discover the promising parts of a search space as extensively as possible [12].”
Optimizing connection weights in neural networks using the whale optimization algorithm (2016, methodology): “In contrast to gradient algorithms, meta-heuristics show higher efficiency in avoiding local minima (Črepinšek et al. 2013; Gang 2013; Mirjalili et al. 2012).”
Grey Wolf Optimizer (2014, background): “Regardless of the differences between the meta-heuristics, a common feature is the division of the search process into two phases: exploration and exploitation [8-12].”
Artificial neural networks in business: Two decades of research (2016, methodology): “However, many other artificial intelligence methods such as simulated annealing [1, 332, 351], particle swarm optimization [289, 377, 425, 432], tabu search [10, 155, 383, 418], or ant colony optimization [280, 313, 347], have been successfully utilized in different research areas like engineering a”
Let a biogeography-based optimizer train your Multi-Layer Perceptron (2014, background): “Each of these strategies has its own advantages and disadvantages that can be useful in a particular application [42].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “There are algorithms inspired by the behavior of animals, birds, and insects, such as gray wolf optimization (GWO) [113], flower pollination (FP) [114], cuckoo search (CS) [115], firefly (FF) [116], etc. Similarly, there are algorithms inspired by some phenomenon observed in the physics and chemistr”