류준규 조정희 김재욱 정연주 박성식 2024-01-12T02:46:05Z 2024-01-12T02:46:05Z 2023-10-30 2023-06 https://pubs.kist.re.kr/handle/201004/76433 https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11522599 This paper presents analyses of the performance of three different search algorithms, including random, greedy, and Bayesian, in the neural architecture search (NAS). To conduct this study, we used Autokeras, a keras-based AutoML framework, to search architectures of deep neural networks (DNNs) and deep spiking neural networks (SNNs). We evaluated the performance of NAS algorithms on searching deep SNNs and DNNs on CIFAR-10 datasets. Our experimental results showed that the Bayesian algorithm outperformed the other two in terms of accuracy, while the greedy algorithm achieved the best accuracy on DNNs. Our findings suggest that the Bayesian algorithm is promising in NAS for both DNNs and SNNs. Korean 대한전자공학회 깊은 스파이킹 신경망을 위한 뉴럴 아키텍처 탐색 알고리즘 성능 분석 Conference 2 2023년도 대한전자공학회 하계종합학술대회 2023년도 대한전자공학회 하계종합학술대회 KO 제주도 2023-06-28 2023년도 대한전자공학회 하계학술대회 논문집