End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior
This work addresses the challenge of modeling human category learning in psychology by integrating stimulus-level representations, which is incremental as it builds on existing cognitive models with deep learning techniques.
The authors tackled the problem of predicting human category learning behavior by extending classic prototype and exemplar models to learn stimulus and category representations jointly from raw input using deep neural networks, resulting in better intrinsic fit to human behavior and improved ground-truth classification compared to typical DNNs.
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.