IntelliSwAS: Optimizing deep neural network architectures using a particle swarm-based approach
作者：
Highlights：
• We propose a novel swarm-based approach for neural architecture search.
• The search technique is enhanced with a model that extends recurrent neural networks.
• The proposed model is able to process data structured as directed acyclic graphs.
• We used image classification for performance-evaluation experiments of the method.
• Our approach surpassed 89.8% of image classification models from the literature.
摘要
•We propose a novel swarm-based approach for neural architecture search.•The search technique is enhanced with a model that extends recurrent neural networks.•The proposed model is able to process data structured as directed acyclic graphs.•We used image classification for performance-evaluation experiments of the method.•Our approach surpassed 89.8% of image classification models from the literature.
论文关键词：Convolutional neural network,Graph neural network,Neural architecture search,Particle swarm optimization,Recurrent neural network
论文评审过程：Received 13 December 2020, Revised 12 April 2021, Accepted 18 September 2021, Available online 23 September 2021, Version of Record 29 September 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115945
