Universal and succinct source coding of deep neural networks
Basu, Sourya
Content Files
BASU-THESIS-2020.pdf
Loading…
Download Files
Loading…
Download Counts (All Files)
Loading…
Edit File
Loading…
Permalink
https://hdl.handle.net/2142/107959
Description
Title
Universal and succinct source coding of deep neural networks
Author(s)
Basu, Sourya
Issue Date
2020-05-04
Director of Research (if dissertation) or Advisor (if thesis)
Varshney, Lav R
Department of Study
Electrical & Computer Eng
Discipline
Electrical & Computer Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2020-08-26T21:54:44Z
Keyword(s)
Deep neural networks
Universal Source Coding
Abstract
Deep neural networks have shown incredible performance for inference tasks in a variety of domains. Unfortunately, most current deep networks are enormous cloud-based structures that require significant storage space, which limits scaling of deep learning as a service (DLaaS) and use for on-device intelligence. This work is concerned with finding universal lossless compressed representations of deep feedforward networks with synaptic weights drawn from discrete sets, and directly performing inference without full decompression. The basic insight that allows less rate than naive approaches is recognizing that the bipartite graph layers of feedforward networks have a kind of permutation invariance to the labeling of nodes, in terms of inferential operation. We provide efficient algorithms to dissipate this irrelevant uncertainty and then use arithmetic coding to nearly achieve the entropy bound in a universal manner. We also provide experimental results of our approach on several standard datasets.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
BASU-THESIS-2020.pdf
