DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices

Resource | v2 | updated by janarez |
Edit
bookmark
Type Paper
Created 2016-04
Available at dx.doi.org/10.1109/ipsn.2016.7460664
Identifier ISBN: 9781509008025
Description

In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX significantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption.

Relations

relates to Deep learning

Deep learning (also known as deep structured learning) is part of a broader family of machine learnin...

about Mobile phone based sensing software

Mobile phone–based sensing software is a class of software for mobile phones that uses the phone's se...

about Deep learning on mobile devices

While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning imp...

Edit details Edit relations Attach new author Attach new topic Attach new resource
6.0 /10
useless alright awesome
from 2 reviews
Write comment Rate resource Tip: Rating is anonymous unless you also write a comment.
Resource level 8.0 /10
beginner intermediate advanced
Resource clarity 6.0 /10
hardly clear sometimes unclear perfectly clear
Reviewer's background 2.5 /10
none basics intermediate advanced expert
Comments 2
janarez
1 0

6 rating 9 level 5 clarity 2 user's background

Cool idea, at least back in 2016. Got nice results that are worth a read if you are interested in optimization of resources.
After reading I don't understand how it works, it's an advanced read.
I actually wonder how this research continued and if it caught on.
jjones
0 0

6 rating 7 level 7 clarity 3 user's background

Interesting idea