Learning signatures of decision making from many individuals playing the same game.

Learning signatures of decision making from many individuals playing the same game.
复制标题

DOI:
10.1109/ner52421.2023.10123846
复制
发表时间:
2023-04
期刊:
International IEEE/EMBS Conference on Neural Engineering : [proceedings]. International IEEE EMBS Conference on Neural Engineering
影响因子:
--
通讯作者:
Dyer, Eva L.
Dyer, Eva L.
中科院分区:
其他
文献类型:
--
作者:
Mendelson, Michael J.;Azabou, Mehdi;Jacob, Suma;Grissom, Nicola;Darrow, David;Ebitz, Becket;Herman, Alexander;Dyer, Eva L.

文献摘要

参考文献

相似文献

人类的行为是非常复杂的,而驱动决策的因素从本能到策略,再到个体之间的偏见,往往会在多个时间尺度上发生变化。在本文中,我们设计了一个预测框架,学习表征编码个人的“行为风格”,即长期行为趋势,同时预测未来的行动和选择。该模型明确地将表征分为三个潜在空间:最近的过去空间,短期空间和长期空间,我们希望在其中捕获个体差异。为了从复杂的人类行为中同时提取全局和局部变量,我们的方法将多尺度时间卷积网络与潜在预测任务相结合,我们鼓励整个序列以及序列子集的嵌入映射到潜在空间中的相似点。我们开发并将我们的方法应用于一个大规模的行为数据集,该数据集来自1,000名玩3臂强盗任务的人类,并分析我们的模型的嵌入结果揭示了人类的决策过程。除了预测未来的选择外,我们还证明了我们的模型可以在多个时间尺度上学习人类行为的丰富表征,并提供个体差异的签名。
Human behavior is incredibly complex and the factors that drive decision making—from instinct, to strategy, to biases between individuals—often vary over multiple timescales. In this paper, we design a predictive framework that learns representations to encode an individual’s ‘behavioral style’, i.e. long-term behavioral trends, while simultaneously predicting future actions and choices. The model explicitly separates representations into three latent spaces: the recent past space, the short-term space, and the long-term space where we hope to capture individual differences. To simultaneously extract both global and local variables from complex human behavior, our method combines a multi-scale temporal convolutional network with latent prediction tasks, where we encourage embeddings across the entire sequence, as well as subsets of the sequence, to be mapped to similar points in the latent space. We develop and apply our method to a large-scale behavioral dataset from 1,000 humans playing a 3-armed bandit task, and analyze what our model’s resulting embeddings reveal about the human decision making process. In addition to predicting future choices, we show that our model can learn rich representations of human behavior over multiple timescales and provide signatures of differences in individuals.
TrajVAE:用于轨迹生成的变分自动编码器模型
DOI: 10.1016/j.neucom.2020.03.120
发表时间: 2021-01-15
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Chen, Xinyu;Xu, Jiajie;Liu, Chengfei
通讯作者: Liu, Chengfei
DOI: 10.1007/11564096_42
发表时间: 2005-01-01
期刊: MACHINE LEARNING: ECML 2005, PROCEEDINGS
影响因子: --
作者:
Vermorel, J;Mohri, M
通讯作者: Mohri, M
DOI: 10.1016/j.jbef.2017.12.004
发表时间: 2018-03-01
影响因子: 6.6
作者:
Palan, Stefan;Schitter, Christian
通讯作者: Schitter, Christian
DOI: 10.1162/089976699300016890
发表时间: 1999-01-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Pentland, A;Liu, A
通讯作者: Liu, A