{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/118034"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/118034","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Neural network simplification using a progressive barrier based approach","abstract":"Neural networks are indispensable to state-of-the-art artificial intelligence algorithms. However, its high accuracy comes at the cost of high computational complexity. This leads to the high operating cost of data centers and also hinders its deployment on mobile devices. In this thesis, we propose an algorithm to address this problem. The proposed algorithm uses progressive barriers to automatically and progressively simplify a pre-trained neural network until the target complexity is met while maximizing the accuracy. Along with the neural network that meets the target complexity, the algorithm also generates a family of simplified networks with different accuracy-complexity trade-offs, which allows for dynamic network selection and further study. Experiment results show that the algorithm achieves better accuracy-complexity trade-offs on a highly compact MobileNet architecture, compared with state-of-the-art automated network simplification approaches. For image classification on the ImageNet dataset, the algorithm reduces the number of multiply-accumulate operations by 1.68x while achieving 0.9% higher accuracy.","abstract_html":"Neural networks are indispensable to state-of-the-art artificial intelligence algorithms. However, its high accuracy comes at the cost of high computational complexity. This leads to the high operating cost of data centers and also hinders its deployment on mobile devices. In this thesis, we propose an algorithm to address this problem. The proposed algorithm uses progressive barriers to automatically and progressively simplify a pre-trained neural network until the target complexity is met while maximizing the accuracy. Along with the neural network that meets the target complexity, the algorithm also generates a family of simplified networks with different accuracy-complexity trade-offs, which allows for dynamic network selection and further study. Experiment results show that the algorithm achieves better accuracy-complexity trade-offs on a highly compact MobileNet architecture, compared with state-of-the-art automated network simplification approaches. For image classification on the ImageNet dataset, the algorithm reduces the number of multiply-accumulate operations by 1.68x while achieving 0.9% higher accuracy.","abstract_has_math":false,"creators":["Yang, Tien-Ju"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Vivienne Sze."],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018","date_published":"2018","updated_at":"2026-07-22T22:21:11Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/118034","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Vivienne Sze."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Yang, Tien-Ju"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-09-17T15:54:41Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-09-17T15:54:41Z"]},{"key":"dc:date.issued","label":"Date","values":["2018"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/118034"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 49-57)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Neural networks are indispensable to state-of-the-art artificial intelligence algorithms. However, its high accuracy comes at the cost of high computational complexity. This leads to the high operating cost of data centers and also hinders its deployment on mobile devices. In this thesis, we propose an algorithm to address this problem. The proposed algorithm uses progressive barriers to automatically and progressively simplify a pre-trained neural network until the target complexity is met while maximizing the accuracy. Along with the neural network that meets the target complexity, the algorithm also generates a family of simplified networks with different accuracy-complexity trade-offs, which allows for dynamic network selection and further study. Experiment results show that the algorithm achieves better accuracy-complexity trade-offs on a highly compact MobileNet architecture, compared with state-of-the-art automated network simplification approaches. For image classification on the ImageNet dataset, the algorithm reduces the number of multiply-accumulate operations by 1.68x while achieving 0.9% higher accuracy."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Neural network simplification using a progressive barrier based approach"]}]}],"canonical_facts":{"dc:contributor.advisor":["Vivienne Sze."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Yang, Tien-Ju"],"dc:date.accessioned":["2018-09-17T15:54:41Z"],"dc:date.available":["2018-09-17T15:54:41Z"],"dc:date.issued":["2018"],"dc:description":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.","Cataloged from PDF version of thesis.","Includes bibliographical references (pages 49-57)."],"dc:description.abstract":["Neural networks are indispensable to state-of-the-art artificial intelligence algorithms. However, its high accuracy comes at the cost of high computational complexity. This leads to the high operating cost of data centers and also hinders its deployment on mobile devices. In this thesis, we propose an algorithm to address this problem. The proposed algorithm uses progressive barriers to automatically and progressively simplify a pre-trained neural network until the target complexity is met while maximizing the accuracy. Along with the neural network that meets the target complexity, the algorithm also generates a family of simplified networks with different accuracy-complexity trade-offs, which allows for dynamic network selection and further study. Experiment results show that the algorithm achieves better accuracy-complexity trade-offs on a highly compact MobileNet architecture, compared with state-of-the-art automated network simplification approaches. For image classification on the ImageNet dataset, the algorithm reduces the number of multiply-accumulate operations by 1.68x while achieving 0.9% higher accuracy."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/118034"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Neural network simplification using a progressive barrier based approach"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:11Z"}