globalchange  > 过去全球变化的重建
DOI: 10.1371/journal.pone.0093250
论文题名:
Deep Belief Networks Learn Context Dependent Behavior
作者: Florian Raudies; Eric A. Zilli; Michael E. Hasselmo
刊名: PLOS ONE
ISSN: 1932-6203
出版年: 2014
发表日期: 2014-3-26
卷: 9, 期:3
语种: 英语
英文关键词: Learning ; Neurons ; Neural networks ; Prefrontal cortex ; Decision tree learning ; Meteorology ; Teachers ; Decision making
英文摘要: With the goal of understanding behavioral mechanisms of generalization, we analyzed the ability of neural networks to generalize across context. We modeled a behavioral task where the correct responses to a set of specific sensory stimuli varied systematically across different contexts. The correct response depended on the stimulus (A,B,C,D) and context quadrant (1,2,3,4). The possible 16 stimulus-context combinations were associated with one of two responses (X,Y), one of which was correct for half of the combinations. The correct responses varied symmetrically across contexts. This allowed responses to previously unseen stimuli (probe stimuli) to be generalized from stimuli that had been presented previously. By testing the simulation on two or more stimuli that the network had never seen in a particular context, we could test whether the correct response on the novel stimuli could be generated based on knowledge of the correct responses in other contexts. We tested this generalization capability with a Deep Belief Network (DBN), Multi-Layer Perceptron (MLP) network, and the combination of a DBN with a linear perceptron (LP). Overall, the combination of the DBN and LP had the highest success rate for generalization.
URL: http://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0093250&type=printable
Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/19136
Appears in Collections:过去全球变化的重建
影响、适应和脆弱性
科学计划与规划
气候变化与战略
全球变化的国际研究计划
气候减缓与适应
气候变化事实与影响

Files in This Item:
File Name/ File Size Content Type Version Access License
journal.pone.0093250.PDF(734KB)期刊论文作者接受稿开放获取View Download

作者单位: Center for Computational Neuroscience and Neural Technology, Boston University, Boston, Massachusetts, United States of America;Center of Excellence for Learning in Education, Science, and Technology, Boston University, Boston, Massachusetts, United States of America;Facebook, Menlo Park, California, United States of America;Center for Computational Neuroscience and Neural Technology, Boston University, Boston, Massachusetts, United States of America;Center of Excellence for Learning in Education, Science, and Technology, Boston University, Boston, Massachusetts, United States of America;Department of Psychology and Graduate Program for Neuroscience, Boston University, Boston, Massachusetts, United States of America

Recommended Citation:
Florian Raudies,Eric A. Zilli,Michael E. Hasselmo. Deep Belief Networks Learn Context Dependent Behavior[J]. PLOS ONE,2014-01-01,9(3)
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[Florian Raudies]'s Articles
[Eric A. Zilli]'s Articles
[Michael E. Hasselmo]'s Articles
百度学术
Similar articles in Baidu Scholar
[Florian Raudies]'s Articles
[Eric A. Zilli]'s Articles
[Michael E. Hasselmo]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[Florian Raudies]‘s Articles
[Eric A. Zilli]‘s Articles
[Michael E. Hasselmo]‘s Articles
Related Copyright Policies
Null
收藏/分享
文件名: journal.pone.0093250.PDF
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.