Chrome Extension
WeChat Mini Program
Use on ChatGLM

Hardware-aware NAS by Genetic Optimisation with a Design Space Exploration Simulator.

CVPR Workshops(2023)

Cited 0|Views18
No score
Abstract
Neural Architecture Search (NAS) has shown its potential in aiding in the development of more efficient neural networks. In regard to hardware, efficiency often equates to power usage or latency. Over the years many researchers have incorporated hardware performance into their NAS experiments. However, accurately modelling hardware performance is a challenge in itself. We look to the field of design space exploration (DSE) for more precise performance metrics on neural network accelerators and incorporate the results into our NAS search. Our experiments show that doing so achieves a significant reduction in latency and energy consumption. The approach we propose also enables detailed insight in the breakdown of the energy consumption and latency of the optimised model.
More
Translated text
Key words
design space exploration simulator,DSE,energy consumption,genetic optimisation model,hardware-aware NAS experiments,neural architecture search,neural network accelerators
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined