Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/39095
Title: | Structured Term Pruning for Computational Efficient Neural Networks Inference | Authors: | Huang, Kai Li, Bowen CHEN, Siang CLAESEN, Luc Xi, Wei Chen , Junjian Jiang, Xiaowen Liu, Zhili Xiong, Dongliang Yan, Xiaolang |
Issue Date: | 2023 | Publisher: | Source: | IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 42 (1) , p. 190 -203 | Abstract: | EEP neural networks (DNNs) have become a powerful algorithm in the region of artificial intelligence, and have shown outstanding performance across a variety of computer vision applications, including image classification [1], object detection [2], and super resolution [3]. However, the inference of DNNs requires vast computing and storage. It is a challenge to deploy the DNNs onto edge devices, which have stringent constraints on resources and energy. | Keywords: | Algorithm-architecture codesign;compression and acceleration;neural networks;quantization;systolic array | Document URI: | http://hdl.handle.net/1942/39095 | ISSN: | 0278-0070 | e-ISSN: | 1937-4151 | DOI: | 10.1109/TCAD.2022.3168506 | ISI #: | 000920800400015 | Rights: | 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information. | Category: | A1 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Structured_Term_Pruning_for_Computational_Efficient_Neural_Networks_Inference.pdf Restricted Access | Published version | 3.14 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.