Comparison of PSO and DE for Training Neural Networks

Espinal, Andrés; Sotelo-Figueroa, Marco Aurelio; Soria-Alcaraz, Jorge A.; Ornelas, Manuel; Soberanes, Héctor José Puga; Carpío, Martín; Baltazar, Rosario; Rico, João

doi:10.1109/micai.2011.16

Cited by 9 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected comparative studies tend to give mixed results and the best choice appears to depend on many factors such as the network size and architecture, see e.g. 33 and 34 .…”

Section: Introductionmentioning

confidence: 85%

Multi-Strategy Coevolving Aging Particle Optimization

Iacca¹,

Caraffini

Neri

2013

Int. J. Neur. Syst.

View full text Add to dashboard Cite

We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization. In a memetic fashion, MS-CAP combines two components with complementary algorithm logics. In the first stage, each particle is perturbed independently along each dimension with a progressively shrinking (decaying) radius, and attracted towards the current best solution with an increasing force. In the second phase, the particles are mutated and recombined according to a multi-strategy approach in the fashion of the ensemble of mutation strategies in Differential Evolution. The proposed algorithm is tested, at different dimensionalities, on two complete black-box optimization benchmarks proposed at the Congress on Evolutionary Computation 2010 and 2013. To demonstrate the applicability of the approach, we also test MS-CAP to train a Feedforward Neural Network modeling the kinematics of an 8-link robot manipulator. The numerical results show that MS-CAP, for the setting considered in this study, tends to outperform the state-of-the-art optimization algorithms on a large set of problems, thus resulting in a robust and versatile optimizer.

show abstract

“…As expected comparative studies tend to give mixed results and the best choice appears to depend on many factors such as the network size and architecture, see e.g. 33 and 34 .…”

Section: Introductionmentioning

confidence: 85%

Multi-Strategy Coevolving Aging Particle Optimization

Iacca¹,

Caraffini

Neri

2013

Int. J. Neur. Syst.

View full text Add to dashboard Cite

show abstract

“…In accordance to the generalization Evolutionary Artificial Neural Networks (EANNs) [23], Evolutionary Spiking Neural Networks (ESNNs) can be specified as a paradigm that involves the utilization of Evolutionary Algorithms to determine the design of Spiking Neural Network approach incorporates the advantages of a metaheuristic process for optimization purposes, and the computing capabilities of third In this approach, a population aspects in the network design to be optimized; the Evolutionary Algorithms capabilities are employed to evolve design criteria such as parameters [24], topology [25], learning rule [26] or a combination of those [27].…”

Section: Evolutionary Spiking Neural Networkmentioning

confidence: 99%

“…In this approach, a population-based algorithm is commonly used to subject a wi aspects in the network design to be optimized; the Evolutionary Algorithms capabilities are employed to evolve design criteria such as parameters [24], topology [25], learning rule [26] or a dology employed in this paper is portrayed in Fig. 2.…”

Section: Evolutionary Spiking Neural Networkmentioning

confidence: 99%

Evolving Random Topologies of Spiking Neural Networks for Pattern Recognition

López-Vázquez¹,

Ornelas-Rodríguez²,

Espinal

et al. 2019

8th International Conference on Soft Computing, Artificial Intelligence and Applications

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) have been successfully used in Pattern Recognition tasks. Evolutionary Spiking Neural Networks (ESNNs) constitute an approach to design thirdgeneration ANNs (also known as Spiking Neural Networks, SNNs) involving Evolutionary Algorithms (EAs) to govern some intrinsic aspects of the networks, such as topology, connections and/or parameters. Concerning the practicality of the networks, a rather simple standard is commonly used; restricted feed-forward fully-connected network topologies deprived from more complex connections are usually considered. Notwithstanding, a wider prospect of configurations in contrast to standard network topologies is available for research. In this paper, ESNNs are evolved to solve pattern classification tasks, using an EA-based algorithm known as Grammatical Evolution (GE). Experiments demonstrate competitive results and a distinctive variety of network designs when compared to a more traditional approach to design ESNNs.

show abstract

“…Thus, the EANNs, in some manner, allow us to avoid or overcome the learnability issues related to ANN architectures and to prescind, partially or completely, of human experts (see [21–24] for comprehensive reviews). There are four main approaches of deploying EANNs [25] by means of weight optimization [26–28], topology structure optimization [25, 29–31], weight and topology structure optimization [32–38], and learning rule optimization [39, 40]. Most of the work made on EANNs is focused on deploying ANNs from the first and second generations.…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Spiking Neural Networks for Solving Supervised Classification Problems

López-Vázquez

Ornelas-Rodríguez

Espinal

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This paper presents a grammatical evolution (GE)-based methodology to automatically design third generation artificial neural networks (ANNs), also known as spiking neural networks (SNNs), for solving supervised classification problems. The proposal performs the SNN design by exploring the search space of three-layered feedforward topologies with configured synaptic connections (weights and delays) so that no explicit training is carried out. Besides, the designed SNNs have partial connections between input and hidden layers which may contribute to avoid redundancies and reduce the dimensionality of input feature vectors. The proposal was tested on several well-known benchmark datasets from the UCI repository and statistically compared against a similar design methodology for second generation ANNs and an adapted version of that methodology for SNNs; also, the results of the two methodologies and the proposed one were improved by changing the fitness function in the design process. The proposed methodology shows competitive and consistent results, and the statistical tests support the conclusion that the designs produced by the proposal perform better than those produced by other methodologies.

show abstract

Comparison of PSO and DE for Training Neural Networks

Cited by 9 publications

References 9 publications

Multi-Strategy Coevolving Aging Particle Optimization

Multi-Strategy Coevolving Aging Particle Optimization

Evolving Random Topologies of Spiking Neural Networks for Pattern Recognition

Evolutionary Spiking Neural Networks for Solving Supervised Classification Problems

Contact Info

Product

Resources

About