Hadjer Benmeziane, Hamza Ouranoughi, S. Niar, Kaoutar El Maghraoui
{"title":"压缩感知神经结构搜索","authors":"Hadjer Benmeziane, Hamza Ouranoughi, S. Niar, Kaoutar El Maghraoui","doi":"10.1109/DSD57027.2022.00059","DOIUrl":null,"url":null,"abstract":"With the ever-growing demand for deep learning (DL) at the edge, building small and efficient DL architectures has become a significant challenge. Optimization techniques such as quantization, pruning or hardware-aware neural architecture search (HW-NAS) have been proposed. In this paper, we present an efficient HW-NAS; Compression-Aware Neural Architecture search (CaW-NAS), that combines the search for the architecture and its quantization policy. While former works search over a fully quantized search space, we define our search space with quantized and non-quantized architectures. Our search strategy finds the best trade-off between accuracy and latency according to the target hardware. Experimental results on a mobile platform show that, our method allows to obtain more efficient networks in terms of accuracy, execution time and energy consumption when compared to the state of the art.","PeriodicalId":211723,"journal":{"name":"2022 25th Euromicro Conference on Digital System Design (DSD)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CaW-NAS: Compression Aware Neural Architecture Search\",\"authors\":\"Hadjer Benmeziane, Hamza Ouranoughi, S. Niar, Kaoutar El Maghraoui\",\"doi\":\"10.1109/DSD57027.2022.00059\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the ever-growing demand for deep learning (DL) at the edge, building small and efficient DL architectures has become a significant challenge. Optimization techniques such as quantization, pruning or hardware-aware neural architecture search (HW-NAS) have been proposed. In this paper, we present an efficient HW-NAS; Compression-Aware Neural Architecture search (CaW-NAS), that combines the search for the architecture and its quantization policy. While former works search over a fully quantized search space, we define our search space with quantized and non-quantized architectures. Our search strategy finds the best trade-off between accuracy and latency according to the target hardware. Experimental results on a mobile platform show that, our method allows to obtain more efficient networks in terms of accuracy, execution time and energy consumption when compared to the state of the art.\",\"PeriodicalId\":211723,\"journal\":{\"name\":\"2022 25th Euromicro Conference on Digital System Design (DSD)\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 25th Euromicro Conference on Digital System Design (DSD)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DSD57027.2022.00059\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 25th Euromicro Conference on Digital System Design (DSD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DSD57027.2022.00059","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
With the ever-growing demand for deep learning (DL) at the edge, building small and efficient DL architectures has become a significant challenge. Optimization techniques such as quantization, pruning or hardware-aware neural architecture search (HW-NAS) have been proposed. In this paper, we present an efficient HW-NAS; Compression-Aware Neural Architecture search (CaW-NAS), that combines the search for the architecture and its quantization policy. While former works search over a fully quantized search space, we define our search space with quantized and non-quantized architectures. Our search strategy finds the best trade-off between accuracy and latency according to the target hardware. Experimental results on a mobile platform show that, our method allows to obtain more efficient networks in terms of accuracy, execution time and energy consumption when compared to the state of the art.