期刊
2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
卷 -, 期 -, 页码 206-213出版社
IEEE
关键词
-
类别
资金
- NSF [ECCS-1405173, IIS-1208623]
- College of Business, University of Texas at Arlington
- King Abdullah Foreign Scholarship
- ARO grant [W911NF-11-D-0001]
A brain-based neural network previously used to model short-term decisions from description is extended to decisions from experience specifically, decisions by a retailer on how much of a product to purchase per day based on cost, price, discounts for large purchases, and feedback about demand on previous days. Learning from feedback is represented in the network by an analog of dopamine neurons' computation of reward prediction error. This is superimposed on a network that includes amygdala and orbitofrontal cortex for emotional evaluation, anterior cingulate for behavioral planning, and striatum, thalamus, and motor cortex for behavioral execution.
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。
推荐
暂无数据