Some recent research reports that a dendritic neuron model (DNM) can achieve better performance than traditional artificial neuron networks (ANNs) on classification, prediction, and other problems when its parameters are well-tuned by a learning algorithm. However, the back-propagation algorithm (BP), as a mostly used learning algorithm, intrinsically suffers from defects of slow convergence and easily dropping into local minima. Therefore, more and more research adopts non-BP learning algorithms to train ANNs. In this paper, a dynamic scale-free network-based differential evolution (DSNDE) is developed by considering the demands of convergent speed and the ability to jump out of local minima. The performance of a DSNDE trained DNM is tested on 14 benchmark datasets and a photovoltaic power forecasting problem. Nine meta-heuristic algorithms are applied into comparison, including the champion of the 2017 IEEE Congress on Evolutionary Computation (CEC2017) benchmark competition effective butterfly optimizer with covariance matrix adapted retreat phase (EBOwithCMAR). The experimental results reveal that DSNDE achieves better performance than its peers.

Yang Yu

College of Automation&College of Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Faculty of Engineering,University of Toyama,Toyama-shi 930-8555,Japan;Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 315211,China;Department of Automation,School of Mechatronic Engineering and Automation,Shanghai University,Shanghai 200444,China

自动化学报（英文版）

[1]Yang Yu-.Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution)[J].自动化学报（英文版）,2022(01):99-110

DSNDE,EBOwithCMAR

Improving,Dendritic,Neuron,Model,With,Dynamic,Scale,Free,Network,Based,Differential,Some,recent,research,reports,that,dendritic,neuron,model,DNM,can,better,performance,than,traditional,artificial,networks,ANNs,classification,prediction,other,problems,when,its,parameters,are,well,tuned,by,learning,However,back,propagation,mostly,used,intrinsically,suffers,from,defects,slow,convergence,easily,dropping,into,local,minima,Therefore,more,adopts,algorithms,In,this,paper,dynamic,scale,free,differential,evolution,developed,considering,demands,convergent,speed,ability,jump,out,trained,tested,benchmark,datasets,photovoltaic,power,forecasting,Nine,meta,heuristic,applied,comparison,including,champion,IEEE,Congress,Evolutionary,Computation,CEC2017,competition,effective,butterfly,optimizer,covariance,matrix,adapted,retreat,phase,experimental,results,reveal,achieves,peers

0.69505