{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:43Z","timestamp":1750220323903,"version":"3.41.0"},"reference-count":0,"publisher":"Association for Computing Machinery (ACM)","issue":"September","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2045685"],"award-info":[{"award-number":["2045685"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Ubiquity"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:p>In this interview, Ubiquity's senior editor Dr. Bushra Anjum chats with Dr. Tengyu Ma, an assistant professor of Computer Science and Statistics at Stanford University. They discuss Dr. Ma's research that aims to bridge the gap between theory and practice in deep learning by developing novel mathematical tools to understand complex and mysterious deep learning systems.<\/jats:p>","DOI":"10.1145\/3486624","type":"journal-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T22:22:55Z","timestamp":1632262975000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A conversation with Tengyu Ma"],"prefix":"10.1145","volume":"2021","author":[{"given":"Bushra","family":"Anjum","sequence":"first","affiliation":[{"name":"Doximity"}]}],"member":"320","published-online":{"date-parts":[[2021,9,21]]},"container-title":["Ubiquity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3486624","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3486624","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3486624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:05Z","timestamp":1750191125000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3486624"}},"subtitle":["developing mathematical tools to understand deep learning systems"],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":0,"journal-issue":{"issue":"September","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.1145\/3486624"],"URL":"https:\/\/doi.org\/10.1145\/3486624","relation":{},"ISSN":["1530-2180"],"issn-type":[{"type":"electronic","value":"1530-2180"}],"subject":[],"published":{"date-parts":[[2021,9]]},"assertion":[{"value":"2021-09-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}