| LDR | | 01865nam u200409 4500 |
| 001 | | 000000422003 |
| 005 | | 20190215165757 |
| 008 | | 181129s2018 |||||||||||||||||c||eng d |
| 020 | |
▼a 9780438296503 |
| 035 | |
▼a (MiAaPQ)AAI10825190 |
| 035 | |
▼a (MiAaPQ)uci:15077 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 247004 |
| 082 | 0 |
▼a 001.5 |
| 100 | 1 |
▼a Nalisnick, Eric Thomas. |
| 245 | 10 |
▼a On Priors for Bayesian Neural Networks. |
| 260 | |
▼a [S.l.]:
▼b University of California, Irvine.,
▼c 2018. |
| 260 | 1 |
▼a Ann Arbor:
▼b ProQuest Dissertations & Theses,
▼c 2018. |
| 300 | |
▼a 156 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B. |
| 500 | |
▼a Adviser: Padhraic Smyth. |
| 502 | 1 |
▼a Thesis (Ph.D.)--University of California, Irvine, 2018. |
| 520 | |
▼a Deep neural networks have bested notable benchmarks across computer vision, reinforcement learning, speech recognition, and natural language processing. However, neural networks still have deficiencies. For instance, they have a penchant to over |
| 520 | |
▼a Bayesian inference is characterized by specification of the prior distribution, and unfortunately, choosing priors for neural networks is difficult. The primary obstacle is that the weights have no intuitive interpretation and seemingly sensible |
| 590 | |
▼a School code: 0030. |
| 650 | 4 |
▼a Artificial intelligence. |
| 650 | 4 |
▼a Statistics. |
| 690 | |
▼a 0800 |
| 690 | |
▼a 0463 |
| 710 | 20 |
▼a University of California, Irvine.
▼b Computer Science. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 80-01B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0030 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T14998739
▼n KERIS
▼z 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a ***1012033 |