Differential evolution training algorithm for dendrite morphological neural networks

Arce, Fernando; Zamora, Erik; Sossa, Humberto; Barron, Randall F.

doi:10.1016/j.asoc.2018.03.033

Cited by 43 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Storn and Price introduced the differential evolution (DE) algorithm in 1995 [18]. DE has been successfully applied to various applications such as pattern recognition, cloud computing, and neural networks [19,20]. MSaDE is an enhanced variant of the DE algorithm with multi-mutation strategies and self-adapting control parameters.…”

Section: An Enhanced Differential Evolution Algorithm With Multimentioning

confidence: 99%

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

Attia¹,

Arafa²,

Sallam³

et al. 2019

IJITCS

View full text Add to dashboard Cite

The demand for workload prediction approaches has recently increased to manage the cloud resources, improve the performance of the cloud services and reduce the power consumption. The prediction accuracy of these approaches affects the cloud performance. In this application paper, we apply an enhanced variant of the differential evolution (DE) algorithm named MSaDE as a learning algorithm to the artificial neural network (ANN) model of the cloud workload prediction. The ANN prediction model based on MSaDE algorithm is evaluated over two benchmark datasets for the workload traces of NASA server and Saskatchewan server at different look-ahead times. To show the improvement in accuracy of training the ANN prediction model using MSaDE algorithm, training is performed with other two algorithms: the back propagation (BP) algorithm and the self-adaptive differential evolution (SaDE) algorithm. Comparisons are made in terms of the root mean squared error (RMSE) and the average root mean squared error (ARMSE) through all prediction intervals. The results show that the ANN prediction model based on the MSaDE algorithm predicts the cloud workloads with higher prediction accuracy than the other algorithms compared with.

show abstract

Section: An Enhanced Differential Evolution Algorithm With Multimentioning

confidence: 99%

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

Attia¹,

Arafa²,

Sallam³

et al. 2019

IJITCS

View full text Add to dashboard Cite

show abstract

“…Apparently unaware of the aforementioned works on MNNs, Franchi et al recently integrated morphological operators with a deep learning framework to introduce the so-called deep morphological network, which is also trained using a steepest descent algorithm [43]. In contrast to steepest descent methods, Arce et al trained MNNs using differential evolution [44]. Moreover, Sussner and Campiotti proposed a hybrid morphological/linear extreme learning machine which has a hidden-layer of morphological units and a linear output layer that is trained by regularized least-squares [45].…”

Section: Introductionmentioning

confidence: 99%

Reduced Dilation-Erosion Perceptron for Binary Classification

Valle

2020

Mathematics

View full text Add to dashboard Cite

Dilation and erosion are two elementary operations from mathematical morphology, a non-linear lattice computing methodology widely used for image processing and analysis. The dilation-erosion perceptron (DEP) is a morphological neural network obtained by a convex combination of a dilation and an erosion followed by the application of a hard-limiter function for binary classification tasks. A DEP classifier can be trained using a convex-concave procedure along with the minimization of the hinge loss function. As a lattice computing model, the DEP classifier assumes the feature and class spaces are partially ordered sets. In many practical situations, however, there is no natural ordering for the feature patterns. Using concepts from multi-valued mathematical morphology, this paper introduces the reduced dilation-erosion (r-DEP) classifier. An r-DEP classifier is obtained by endowing the feature space with an appropriate reduced ordering. Such reduced ordering can be determined using two approaches: One based on an ensemble of support vector classifiers (SVCs) with different kernels and the other based on a bagging of similar SVCs trained using different samples of the training set. Using several binary classification datasets from the OpenML repository, the ensemble and bagging r-DEP classifiers yielded in mean higher balanced accuracy scores than the linear, polynomial, and radial basis function (RBF) SVCs as well as their ensemble and a bagging of RBF SVCs.

show abstract

“…Because of these characteristics and the advantages of DE, it has been recognized by scholars in the field of ANNs [36,37]. Also, DE has been applied in dendrite morphological neural networks [38].…”

Section: Introductionmentioning

confidence: 99%

A Dendritic Neuron Model with Adaptive Synapses Trained by Differential Evolution Algorithm

Wang

Gao

Wang

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A dendritic neuron model with adaptive synapses (DMASs) based on differential evolution (DE) algorithm training is proposed. According to the signal transmission order, a DNM can be divided into four parts: the synaptic layer, dendritic layer, membrane layer, and somatic cell layer. It can be converted to a logic circuit that is easily implemented on hardware by removing useless synapses and dendrites after training. This logic circuit can be designed to solve complex nonlinear problems using only four basic logical devices: comparators, AND (conjunction), OR (disjunction), and NOT (negation). To obtain a faster and better solution, we adopt the most popular DE for DMAS training. We have chosen five classification datasets from the UCI Machine Learning Repository for an experiment. We analyze and discuss the experimental results in terms of the correct rate, convergence rate, ROC curve, and the cross-validation and then compare the results with a dendritic neuron model trained by the backpropagation algorithm (BP-DNM) and a neural network trained by the backpropagation algorithm (BPNN). The analysis results show that the DE-DMAS shows better performance in all aspects.

show abstract

Differential evolution training algorithm for dendrite morphological neural networks

Cited by 43 publications

References 15 publications

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

Reduced Dilation-Erosion Perceptron for Binary Classification

A Dendritic Neuron Model with Adaptive Synapses Trained by Differential Evolution Algorithm

Contact Info

Product

Resources

About