인공신경망 가중치의 효과적인 최적화를 위한 하이브리드 메타휴리스틱 알고리즘 (An Effective Hybrid Metaheuristic Algorithm for Weight Optimization of Artificial Neural Networks)

서지정보

· 발행기관 : 대한산업공학회
· 수록지 정보 : 대한산업공학회지 / 48권 / 2호 / 227 ~ 234페이지
· 저자명 : 고광종, 허재석

초록

Due to a number of local minimums, the gradient descent methods have difficulties in searching for the optimal weights of artificial neural networks (ANNs). To resolve this problem, recently, a number of scholars have conducted studies that utilize metaheuristics to optimize the weights of ANNs. Particularly, the swarm intelligence algorithm which is one of the metaheuristics has shown great potential in previous studies. In this study, we propose the hybrid metaheuristic algorithm that effectively optimizes the weight of ANNs by combining particle swarm optimization (PSO) and grey wolf optimizer (GWO), both of which are swarm intelligence algorithms. In the search process, the proposed algorithm resolves the convergence instability in the validation dataset using the swarm memory that was inspired by the habit of remembering the environment in which the swarm was suitable for survival. Numerical experiments demonstrate the proposed algorithm outperforms the existing swarm intelligence algorithms, stochastic gradient descent, and Adam Optimizer in terms of classification accuracy.

영어초록

Due to a number of local minimums, the gradient descent methods have difficulties in searching for the optimal weights of artificial neural networks (ANNs). To resolve this problem, recently, a number of scholars have conducted studies that utilize metaheuristics to optimize the weights of ANNs. Particularly, the swarm intelligence algorithm which is one of the metaheuristics has shown great potential in previous studies. In this study, we propose the hybrid metaheuristic algorithm that effectively optimizes the weight of ANNs by combining particle swarm optimization (PSO) and grey wolf optimizer (GWO), both of which are swarm intelligence algorithms. In the search process, the proposed algorithm resolves the convergence instability in the validation dataset using the swarm memory that was inspired by the habit of remembering the environment in which the swarm was suitable for survival. Numerical experiments demonstrate the proposed algorithm outperforms the existing swarm intelligence algorithms, stochastic gradient descent, and Adam Optimizer in terms of classification accuracy.

참고자료

· 없음