상세정보
Export to Refworks부가기능
Learning Along the Edge of Deep Neural Networks
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Learning Along the Edge of Deep Neural Networks. |
| 개인저자 | Kabkab, Maya. |
| 단체저자명 | University of Maryland, College Park. Electrical Engineering. |
| 발행사항 | [S.l.]: University of Maryland, College Park., 2018. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
| 형태사항 | 157 p. |
| 기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
| ISBN | 9780438144613 |
| 학위논문주기 | Thesis (Ph.D.)--University of Maryland, College Park, 2018. |
| 일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Adviser: Rama Chellappa. |
| 요약 | While Deep Neural Networks (DNNs) have recently achieved impressive results on many classification tasks, it is still unclear why they perform so well and how to properly design them. It has been observed that while training and testing deep net |
| 요약 | In this dissertation, we analyze each of these individual conditions to understand their effects on the performance of deep networks. Furthermore, we devise mitigation strategies when the ideal conditions may not be met. |
| 요약 | We, first, investigate the relationship between the performance of a convolutional neural network (CNN), its depth, and the size of its training set. Designing a CNN is a challenging task and the most common approach to picking the right archite |
| 요약 | Next, we study the structure of the CNN layers, by examining the convolutional, activation, and pooling layers, and showing a parallelism between this structure and another well-studied problem: Convolutional Sparse Coding (CSC). The sparse repr |
| 요약 | Then, we investigate three of the ideal conditions previously mentioned: the availability of vast amounts of noiseless and balanced training data. We overcome the difficulties resulting from deviating from this ideal scenario by modifying the tr |
| 요약 | Finally, we consider the case where testing (and potentially training) samples are lossy, leading to the well-known compressed sensing framework. We use Generative Adversarial Networks (GANs) to impose structure in compressed sensing problems, r |
| 일반주제명 | Computer science. Electrical engineering. Artificial intelligence. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
