상세정보
Export to Refworks부가기능
Advances in Deep Generative Modeling with Applications to Image Generation and Neuroscience
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Advances in Deep Generative Modeling with Applications to Image Generation and Neuroscience. |
| 개인저자 | Loaiza Ganem, Gabriel. |
| 단체저자명 | Columbia University. Statistics. |
| 발행사항 | [S.l.]: Columbia University., 2019. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
| 형태사항 | 132 p. |
| 기본자료 저록 | Dissertations Abstracts International 81-05B. Dissertation Abstract International |
| ISBN | 9781687927316 |
| 학위논문주기 | Thesis (Ph.D.)--Columbia University, 2019. |
| 일반주기 |
Source: Dissertations Abstracts International, Volume: 81-05, Section: B.
Advisor: Cunningham, John P. |
| 이용제한사항 | This item must not be sold to any third party vendors. |
| 요약 | Deep generative modeling is an increasingly popular area of machine learning that takes advantage of recent developments in neural networks in order to estimate the distribution of observed data. In this dissertation we introduce three advances in this area. The first one, Maximum Entropy Flow Networks, allows to do maximum entropy modeling by combining normalizing flows with the augmented Lagrangian optimization method. The second one is the continuous Bernoulli, a new [0,1]-supported distribution which we introduce with the motivation of fixing the pervasive error in variational autoencoders of using a Bernoulli likelihood for non-binary data. The last one, Deep Random Splines, is a novel distribution over functions, where samples are obtained by sampling Gaussian noise and transforming it through a neural network to obtain the parameters of a spline. We apply these to model texture images, natural images and neural population data, respectively |
| 일반주제명 | Statistics. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
