| LDR | | 02195nam u200445 4500 |
| 001 | | 000000418583 |
| 005 | | 20190215163000 |
| 008 | | 181129s2018 |||||||||||||||||c||eng d |
| 020 | |
▼a 9780438291706 |
| 035 | |
▼a (MiAaPQ)AAI10843897 |
| 035 | |
▼a (MiAaPQ)ucla:17157 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 247004 |
| 082 | 0 |
▼a 001.5 |
| 100 | 1 |
▼a Chaudhari, Pratik Anil. |
| 245 | 12 |
▼a A Picture of the Energy Landscape of Deep Neural Networks. |
| 260 | |
▼a [S.l.]:
▼b University of California, Los Angeles.,
▼c 2018. |
| 260 | 1 |
▼a Ann Arbor:
▼b ProQuest Dissertations & Theses,
▼c 2018. |
| 300 | |
▼a 175 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B. |
| 500 | |
▼a Adviser: Stefano Soatto. |
| 502 | 1 |
▼a Thesis (Ph.D.)--University of California, Los Angeles, 2018. |
| 520 | |
▼a This thesis characterizes the training process of deep neural networks. We are driven by two apparent paradoxes. First, optimizing a non-convex function such as the loss function of a deep network should be extremely hard, yet rudimentary algori |
| 520 | |
▼a We build upon tools from two main areas to make progress on these questions: statistical physics and a continuous-time point-of-view of optimization. The former has been popular in the study of machine learning in the past and has been rejuvenat |
| 520 | |
▼a The confluence of these ideas leads to fundamental theoretical insights that explain observed phenomena in deep learning as well as the development of state-of-the-art algorithms for training deep networks. |
| 590 | |
▼a School code: 0031. |
| 650 | 4 |
▼a Artificial intelligence. |
| 650 | 4 |
▼a Applied mathematics. |
| 650 | 4 |
▼a Statistical physics. |
| 690 | |
▼a 0800 |
| 690 | |
▼a 0364 |
| 690 | |
▼a 0217 |
| 710 | 20 |
▼a University of California, Los Angeles.
▼b Computer Science 0201. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 80-01B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0031 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T14999954
▼n KERIS
▼z 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a ***1012033 |