End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior
End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior
复制标题
DOI：
--
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Pulkit Singh;Joshua C. Peterson;Ruairidh M. Battleday;T. Griffiths
中科院分区：
文献类型：
--
作者：
Pulkit Singh;Joshua C. Peterson;Ruairidh M. Battleday;T. Griffiths
传统的心理学类别学习模型关注的是类别层面的表征，而不是刺激层面的表征，尽管两者可能会相互作用。这些模型中使用的刺激表征要么是由实验者手工设计的，要么是从人类判断中间接推断出来的，要么是从预先训练好的深度神经网络中借来的，这些深度神经网络本身就是类别学习的竞争模型。在这项工作中，我们扩展了经典的原型和范例模型，从原始输入中学习刺激和类别表征。这类新模型可以通过深度神经网络（DNN）进行参数化，并进行端到端的训练。根据它们的名字，我们将它们称为深度原型模型，深度样本模型和深度高斯混合模型。与典型的DNN相比，我们发现它们的认知启发对应物都提供了更好的内在拟合人类行为，并改善了地面实况分类。
Traditional models of category learning in psychology focus on representation at the category level as opposed to the stimulus level, even though the two are likely to interact. The stimulus representations employed in such models are either hand-designed by the experimenter, inferred circuitously from human judgments, or borrowed from pretrained deep neural networks that are themselves competing models of category learning. In this work, we extend classic prototype and exemplar models to learn both stimulus and category representations jointly from raw input. This new class of models can be parameterized by deep neural networks (DNN) and trained end-to-end. Following their namesakes, we refer to them as Deep Prototype Models, Deep Exemplar Models, and Deep Gaussian Mixture Models. Compared to typical DNNs, we find that their cognitively inspired counterparts both provide better intrinsic fit to human behavior and improve ground-truth classification.