Approximations in Deep Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Book Sections Year : 2022

Approximations in Deep Learning

Abstract

The design and implementation of Deep Learning (DL) models is currently receiving a lot of attention from both industrials and academics. However, the computational workload associated with DL is often out of reach for low-power embedded devices and is still costly when run on datacenters. By relaxing the need for fully precise operations, Approximate Computing (AxC) substantially improves performance and energy efficiency. DL is extremely relevant in this context, since playing with the accuracy needed to do adequate computations will significantly enhance performance, while keeping the quality of results in a user-constrained range. This chapter will explore how AxC can improve the performance and energy efficiency of hardware accelerators in DL applications during inference and training.
Fichier principal
Vignette du fichier
chapter15/chapter_15.pdf (1.75 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03494874 , version 1 (07-12-2022)

Identifiers

Cite

Etienne Dupuis, Silviu-Ioan Filip, Olivier Sentieys, David Novo, Ian O'Connor, et al.. Approximations in Deep Learning. Approximate Computing Techniques - From Component- to Application-Level, pp.467-512, 2022, 978-3-030-94704-0. ⟨10.1007/978-3-030-94705-7_15⟩. ⟨hal-03494874⟩
167 View
86 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More