Neural nets in a group decision process
Neural nets in a group decision process
复制标题
群体决策过程中的神经网络
DOI：
10.1007/s001820300130
复制
发表时间：
2003
影响因子：
0.6
通讯作者：
P. Ein
中科院分区：
文献类型：
--
作者：
M. Leshno;David Moller;P. Ein
近年来，将人工适应智能体(AAA)应用于复杂适应系统，特别是经济系统的研究引起了人们的兴趣。神经网络经常被用作AAA。人工神经网络模仿人脑的物理结构和信息处理的某些方面，它们最吸引人的特征是它们从一组给定的例子中学习模式的能力。在这项研究中，我们研究了神经网络在群体决策过程中对人类行为进行建模的能力。背景是一个具有线性支付函数和二元决策的市场进入博弈。对于每一次审判，参与者必须决定是否进入一个能力为公众所知的市场。在这种情况下，人类的行为已经通过非合作人博弈的纳什均衡进行了建模和经验验证。游戏的模拟是用神经网络代替人类受试者进行的。使用他们参加的比赛的结果对这些网进行了训练。用神经网络组进行的模拟显示了与在人类玩家组中观察到的现象非常相似的现象。
In recent years there has been some interest in applying Artificial Adaptive Agents (AAA) to the study of complex adaptive systems, especially economic systems. Neural networks are frequently employed as AAA. Artificial neural nets mimic certain aspects of the physical structure and information processing of the human brain and their most attractive characteristic is their ability to learn a pattern from a given set of examples. In this study, we investigated the ability of neural nets to model human behavior in a group decision process. The context was a market entry game with a linear payoff function and binary decisions. The players had to decide, for each trial, whether or not to enter a market whose capacity is public knowledge. Human behavior in this situation has been modeled and empirically validated by the Nash equilibrium for noncooperativen-person games. A simulation of the game was performed with neural nets instead of human subjects. The nets were trained using the results of the games in which they participated. The simulation with groups of neural nets exhibits phenomena very similar to those observed in groups of human players.