A hybrid of genetic algorithm and particle swarm optimization for recurrent network design

By Chia-Feng Juang. 2004

993 citations recorded by the source corpus.

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

Deep learning in neural networks: An overview (2014, background): “In practical applications, however, current artificial networks of spiking neurons cannot yet compete with the best traditional deep NNs (e.g., compare MNIST results of Section 5.19).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1 RL through Direct and Indirect Search in RNN Program Space It is possible to train small RNNs with a few 100 or 1000 weights using evolutionary algorithms [200, 255, 105, 56, 68] to search the space of NN weights [165, 307, 44, 321, 180, 259, 320, 164, 173, 69, 71, 187, 121, 313, 66, 270, 269, 305”
Orthogonal Learning Particle Swarm Optimization (2009, methodology): “Hybridization of PSO with GA has also been applied to recurrent artificial neural network design [28].”
Evaluation of Differential Evolution and Particle Swarm Optimization Algorithms at Training of Neural Network for prediction (2014, methodology): “[18] One possibility could be a hybrid of traditional optimization methods and evolutionary algorithms as studied in [2, 4, 11].”
A Competitive Swarm Optimizer for Large Scale Optimization (2015, methodology): “One straightforward idea is to combine PSO with different evolutionary algorithms, such as genetic algorithms [26], differential evolution [27], and ant colony optimization [28], [29].”
Particle Swarm Optimization: A survey of historical and recent developments with hybridization perspectives (2018, methodology): “mization Krink and Løvbjerg [41] 2002 Life Cycle Model Unconstrained global optimization Conradie et al. [42] 2002 SMNE Neural Networks Grimaldi et al. [43] 2004 GSO Electromagnetic Application Juang [44] 2004 GA-PSO Network Design Settles and Soule [45] 2005 Breeding Swarm Unconstrained Global Opti”
Adaptive Particle Swarm Optimization (2008, methodology): “Hybridization of GA and PSO has been used in [38] for recurrent artificial neural network design.”
Genetic Learning Particle Swarm Optimization (2016, methodology): “Furthermore, GA-PSO hybrid algorithms have been developed to tackle some ad hoc applications, including recurrent network design [19], electromagnetic structure optimization [20], and conformal array pattern synthesis [21].”
A hybrid genetic algorithm and bacterial foraging approach for global optimization (2007, background): “Function P i c ð / Þ , i = 1,2, . . . , S , to model the cell-to-cell signaling via an attractant and a repellant is represented by [23,39,36,37] where / = [ / 1 , . . . , / p ] T is a point on the search space, L attract is the depth of the attractant released by the cell and d attract is a…”
Accurate, Robust, and Flexible Real-time Hand Tracking (2015, methodology): “MODEL FITTING In order to optimize the golden energy and achieve an accurate hand pose estimate, we employ a model fitting algorithm that combines features of particle swarm optimization (PSO) and genetic algorithms (GA) in the spirit of [11, 17, 20].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “A hybrid GA and PSO approach for optimizing the FNN were proposed in [131], where both GA and PSO were suggested to run over the same population—randomly generated population W of m individuals (the same individual was treated as a chromosome in GA and a particle in PSO).”
A review of population-based meta-heuristic algorithm (2013, methodology): “Also, hybridization of GA and PSO has been applied [73] for recurrent artiﬁcial neural network design.”