HSCoNAS : hardware-software co-design of efficient DNNs via neural architecture search

• المؤلفون الرئيسيون: Luo, Xiangzhong, Liu, Di, Huai, Shuo, Liu, Weichen
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Computer science and engineering; Performance Evaluation; Runtime
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/155784
• المؤسسة: Nanyang Technological University

In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware. To accomplish this goal, we first propose an effective hardware...