Year: 2023
Type: preprint
Abstract: Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple metrics. In this paper, we propose that, on top of these approaches, it could be beneficial for NAS optimization of resource constrained systems to also consider input data granularity. We name such a system "Data Aware NAS", and we provide experimental evidence of its benefits by comparing it to traditional NAS.
Source: arXiv (Cornell University)
Authors: Njor, Emil, Madsen, Jan, Fafoutis, Xenofon
Institution: Technical University of Denmark
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Innovationsfonden
Award: G4782604025
OpenAlex ID: W4362655878