4.7 Article

Learning to represent a multi-context environment: more than detecting changes

期刊

FRONTIERS IN PSYCHOLOGY
卷 3, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fpsyg.2012.00228

关键词

multi-context environment; contextual ambiguity; representation learning; contextual cue; change detection

资金

  1. Div Of Information & Intelligent Systems [1150028] Funding Source: National Science Foundation
  2. EUNICE KENNEDY SHRIVER NATIONAL INSTITUTE OF CHILD HEALTH & HUMAN DEVELOPMENT [R01HD037082, R01HD067250] Funding Source: NIH RePORTER
  3. NICHD NIH HHS [R01 HD067250, R01 HD037082] Funding Source: Medline

向作者/读者索取更多资源

Learning an accurate representation of the environment is a difficult task for both animals and humans, because the causal structures of the environment are unobservable and must be inferred from the observable input. In this article, we argue that this difficulty is further increased by the multi-context nature of realistic learning environments. When the environment undergoes a change in context without explicit cueing, the learner must detect the change and employ a new causal model to predict upcoming observations correctly. We discuss the problems and strategies that a rational learner might adopt and existing findings that support such strategies. We advocate hierarchical models as an optimal structure for retaining causal models learned in past contexts, thereby avoiding relearning familiar contexts in the future.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据