Artificial Neural Networks - ICANN 2010
Artificial Neural Networks - ICANN 2010
复制标题
人工神经网络 - ICANN 2010
DOI：
10.1007/978-3-642-15822-3_23
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Brohan K
中科院分区：
文献类型：
--
作者：
Brohan K
我们提出了一个生物启发的神经网络模型的视觉定向（使用扫视眼球运动），其中目标优先选择根据其奖励值。引导扫视的视觉特征的内部表征是在自组织地图中开发的，其可塑性在奖励下被调制。以这种方式，仅生成与获取奖励目标相关的那些特征。除了引导特征表征的形成外，奖励刺激还存储在工作记忆中，并使未来的扫视产生偏差。此外，奖励预测误差用于启动自组织映射的再训练，以在必要时生成更有效的特征表示。
We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward value. Internal representations of visual features that guide saccades are developed in a self-organised map whose plasticity is modulated under reward. In this way, only those features relevant for acquiring rewarding targets are generated. As well as guiding the formation of feature representations, rewarding stimuli are stored in a working memory and bias future saccade generation. In addition, a reward prediction error is used to initiate retraining of the self-organised map to generate more efficient representations of the features when necessary.