Publication detail

ApproxDARTS: Differentiable Neural Architecture Search with Approximate Multipliers

PIŇOS, M. SEKANINA, L. MRÁZEK, V.

Original Title

ApproxDARTS: Differentiable Neural Architecture Search with Approximate Multipliers

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

Integrating the principles of approximate computing into the design of hardware-aware deep neural networks (DNN) has led to DNNs implementations showing good output quality and highly optimized hardware parameters such as low latency or inference energy. In this work, we present ApproxDARTS, a neural architecture search (NAS) method enabling the popular differentiable neural architecture search method called DARTS to exploit approximate multipliers and thus reduce the power consumption of generated neural networks. We showed on the CIFAR-10 data set that the ApproxDARTS is able to perform a complete architecture search within less than 10 GPU hours and produce competitive convolutional neural networks (CNN) containing approximate multipliers in convolutional layers. For example, ApproxDARTS created a CNN showing an energy consumption reduction of (a) 53.84% in the arithmetic operations of the inference phase compared to the CNN utilizing the native 32-bit floating-point multipliers and (b) 5.97% compared to the CNN utilizing the exact 8-bit fixed-point multipliers, in both cases with a negligible accuracy drop. Moreover, the ApproxDARTS is 2.3 times faster than a similar but evolutionary algorithm-based method called EvoApproxNAS.

Keywords

Neural Architecture Search, Convolutional Neural Networks, Approximate Computing, Machine Learning

Authors

PIŇOS, M.; SEKANINA, L.; MRÁZEK, V.

Released

30. 1. 2024

URL

https://arxiv.org/abs/2404.08002

BibTex

@inproceedings{BUT188465,
  author="Michal {Piňos} and Lukáš {Sekanina} and Vojtěch {Mrázek}",
  title="ApproxDARTS: Differentiable Neural Architecture Search with Approximate Multipliers",
  booktitle="The International Joint Conference on Neural Networks",
  year="2024",
  url="https://arxiv.org/abs/2404.08002"
}