Sensitivity Analysis and Compression Opportunities in DNNs Using Weight Sharing - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2020

Sensitivity Analysis and Compression Opportunities in DNNs Using Weight Sharing

Abstract

Deep artificial Neural Networks (DNNs) are currently one of the most intensively and widely used predictive models in the field of machine learning. However, the computational workload involved in DNNs is typically out of reach for lowpower embedded devices. The approximate computing paradigm can be exploited to reduce the DNN complexity. It improves performance and energy-efficiency by relaxing the need for fully accurate operations. There are a large number of implementation options leveraging many approximation techniques (e.g., pruning, quantization, weight-sharing, low-rank factorization, knowledge distillation, etc.). However, to the best of our knowledge, a few or no automated approach exists to explore, select and generate the best approximate version of a given DNN according to design objectives. The goal of this paper is to demonstrate that the design space exploration phase can enable significant network compression without noticeable accuracy loss. We demonstrate this via an example based on weight sharing and show that our direct conversion method can obtain a 4.85x compression rate with 0.14% accuracy loss in ResNet18 and 4.91x compression rate with 0.44% accuracy loss in SqueezeNet without involving retraining steps.
Fichier principal
Vignette du fichier
DDESC_2020_submission_paper (1).pdf (615.5 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

lirmm-03054134 , version 1 (11-12-2020)

Identifiers

Cite

Etienne Dupuis, David Novo, Ian O'Connor, Alberto Bosio. Sensitivity Analysis and Compression Opportunities in DNNs Using Weight Sharing. DDECS 2020 - 23rd International Symposium on Design and Diagnostics of Electronic Circuits and Systems, Apr 2020, Novi Sad, Serbia. pp.1-6, ⟨10.1109/DDECS50862.2020.9095658⟩. ⟨lirmm-03054134⟩
67 View
294 Download

Altmetric

Share

More