자료유형  

 학위논문

Control Number  

0016931747

International Standard Book Number  

9798379761950

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Schwarzschild, Avi.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of Maryland, College Park., 2023

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2023

Physical Description  

1 online resource(124 p.)

General Note  

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

General Note  

Advisor: Goldstein, Tom.

Dissertation Note  

Thesis (Ph.D.)--University of Maryland, College Park, 2023.

Restrictions on Access Note  

This item must not be sold to any third party vendors.

Summary, Etc.  

요약Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans are still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. We study neural networks that have exactly this capability. By employing recurrence, we build neural networks that can expend more computation when needed. Using several datasets designed specifically for studying generalization from easy problems to harder test samples, we show that our recurrent networks can extrapolate from easy training data to much harder examples at test time, and they do so with many more iterations of a recurrent block of layers than are used during training.

Subject Added Entry-Topical Term  

Computer science.

Index Term-Uncontrolled  

Deep neural networks

Index Term-Uncontrolled  

Recurrent networks

Index Term-Uncontrolled  

Training

Added Entry-Corporate Name  

University of Maryland, College Park Mathematics

Host Item Entry  

Dissertations Abstracts International. 84-12B.

Host Item Entry  

Dissertation Abstract International

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:639255