Uncertainty and learning
Uncertainty and learning
复制标题
DOI：
10.1080/03772063.2003.11416335
复制
发表时间：
2003-03-01
影响因子：
1.5
通讯作者：
Yu, AJ
中科院分区：
文献类型：
--
作者：
Dayan, P;Yu, AJ
参数的不确定性推动学习，这在统计学上是司空见惯的。事实上，它们中最具影响力的行为学习模式之一，其核心是不确定性。然而，许多流行的学习理论模型只关注错误，而忽视了不确定性。在这里，我们从三个角度回顾学习和不确定性之间的联系：统计理论，如卡尔曼滤波，心理学模型，其中不同的注意刺激对与这些刺激相关的学习速度的影响，以及关于神经调节剂影响的神经生物学数据；乙酰胆碱和去甲肾上腺素对学习和推理的影响。
It is a commonplace in statistics that uncertainty about parameters drives learning. Indeed one of them most influential models of behavioural learning has uncertainty at its heart. However, many popular theoretical models of learning focus exclusively on error, and ignore uncertainty. Here we review the links between learning and uncertainty from three perspectives: statistical theories such as the Kalman filter, psychological models in which differential attention is paid to stimuli with an effect on the speed of learning associated with those stimuli, and neurobiological data on the influence of the neuromodulators; acetylcholine and norepinephrine on learning and inference.