在隐藏原因的神经网络模型中,调和共享与特定背景信息
Qihong Lu1, Tan T Nguyen2, Qiong Zhang3
1Department of Psychology and Princeton Neuroscience Institute, Princeton University, Princeton, USA. qihong.lu@columbia.edu.
本研究介绍了潜在原因网络 (LCNet),这是一个模型,可以同时学习共享和特定环境的结构. 在各种任务中,LCNet成功地解释了人类学习和事件结构推断.
科学领域:
- 认知科学 认知科学
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
背景情况:
- 人类将经验细分为潜在原因 (LC),以实现上下文依赖的学习.
- 整合跨语境的共享结构与LC分割仍然是一个挑战.
研究的目的:
- 介绍潜在原因网络 (LCNet),用于LC推断的神经网络模型.
- 证明LCNet能够协调共享和特定环境结构学习的能力.
主要方法:
- 开发了LCNet,一个神经网络模型,包含了上下文模块和贝叶斯非参数推理.
- 通过三个模拟来评估LCNet:函数学习,模式学习和自然视频事件推理.
主要成果:
- LCNet成功地在LC中提取了共享结构,防止了功能学习的灾难性干扰.
- 该模型捕获了关于课程效应在模式学习中的人类数据.
- LCNet从自然主义的日常事件视频中推断出潜在的事件结构.
结论:
- LCNet提供了一个计算可行的方法来建模共享和特定环境结构的同时学习.
- 该模型展示了从受控实验到现实世界自然环境的可扩展性.
更多相关视频
11:18Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
相关概念视频
Cause and Effect
Purposive Learning
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Real-World Application of Classical Conditioning
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
Correlation and Causation
Correlation versus Causation
If the dependent variable increases or decreases when the independent variable increases, there is a positive or negative...
Psychological and Sociocultural Causes of Schizophrenia
