Compiler-level approximate mobile computing

master's thesis

Matevž Fabjančič (Author), Veljko Pejović (Mentor)

Abstract

With the widespread use of smartphones, wearable devices and many applications of deep learning (DL), there is a growing interest in deploying DL on low-power devices. However, due to inferior computational resources and battery capacity limitations, this is a challenging task. One solution to this problem stems from approximate computing – by using approximations, we can sacrifice accuracy for better energy-efficiency. We develop an end-to-end system for adaptive approximate mobile computing (AMC), which enables transforming high-level definitions of convolutional neural networks into approximable DL models suitable for deployment within Android applications. We define ways of adaptively selecting among approximation levels to achieve better energy-efficiency of DL on smartphones while preserving the option of using non-approximated neural network variants. We evaluate the benefits of adaptive AMC on a concrete use case.

Keywords

ubiquitous computing;adaptive approximations;approximate computing;compilers;Android;deep learning;computer science;computer and information science;master's thesis;

Data

Language:	English
Year of publishing:	2021
Typology:	2.09 - Master's Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[M. Fabjančič]
UDC:	004.382.73/.77(043.2)
COBISS:	84027395
Views:	233
Downloads:	49
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary title:	Približno računanje na ravni prevajalnika na mobilnih napravah
Secondary abstract:	Razširjenost pametnih naprav, kot so telefoni in ure, skupaj z množično uporabo aplikacij globokega učenja kličeta po uporabi modelov globokega učenja na napravah nizke zmogljivosti. Zaradi računske zahtevnosti globokega učenja pa je to na napravah z omejenimi računskimi viri težko izvedljivo. Z vpeljavo približnega računanja v modele globokega učenja lahko za ceno natančnosti modelov prihranimo na porabljeni energiji. V tej nalogi razvijemo enoviti sistem za prilagodljivo približno računanje na mobilnih napravah. Sistem omogoča, da visoko nivojske opise nevronskih mrež pretvorimo v modele z nastavljivo približnostjo in jih uporabimo v aplikacijah za naprave z operacijskim sistemom Android. Na primeru uporabe pokažemo, da lahko z različnimi sistemi samodejnega prilagajanja približnosti modelov dosežemo boljšo energijsko učinkovitost modelov na mobilnih napravah in ohranimo možnost klasifikacije z neaproksimirano nevronsko mrežo.
Secondary keywords:	vseprisotno računanje;prilagodljivo aproksimiranje;približno računanje;prevajalniki;Android;globoko učenje;računalništvo in informatika;magisteriji;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS):	Master's thesis/paper
Study programme:	1000471
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	VIII, 66 str.
ID:	13826395