Deep neural network models of emotion understanding

Deep neural networks (DNNs) provide a useful computational framework for constructing cognitive models of emotion understanding. This paper provides a focused discussion of the use of DNNs in this context. It begins by defining three key components of emotion understanding – perception, prediction, and regulation – and discussing how each can be modeling using different deep learning architectures. It continues by positioning what DNN models can contribute to affective science in relation to important existing theoretical perspectives, including both domain-general frameworks like Bayesian cognitive modeling, and domain-specific frameworks, such as the theory of constructed emotion. The paper highlights both the strengths and limitations of DNNs as cognitive models and provides guidance for how to capitalize on the former while mitigating the latter.