Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution

Yang Yu

doi:10.1109/JAS.2021.1004284

Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution

2022-01-01

58

PRE

AI

DOI：10.1109/JAS.2021.1004284

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Artificial neuron networks (ANNs)

dendrite neuron network

differential evolution (DE)

scale-free network

Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution

Abstract

Journal

Organization