How can deep learning advance computational modeling of sensory information processing?
This work provides methodological clarity for researchers in computational neuroscience and cognitive science, though it is incremental in nature.
The paper addresses the challenge of interpreting statistical conclusions when using deep neural networks (DNNs) as models of sensory information processing, clarifying the types of conclusions possible and proposing new techniques for stronger insights into computational mechanisms.
Deep learning, computational neuroscience, and cognitive science have overlapping goals related to understanding intelligence such that perception and behaviour can be simulated in computational systems. In neuroimaging, machine learning methods have been used to test computational models of sensory information processing. Recently, these model comparison techniques have been used to evaluate deep neural networks (DNNs) as models of sensory information processing. However, the interpretation of such model evaluations is muddied by imprecise statistical conclusions. Here, we make explicit the types of conclusions that can be drawn from these existing model comparison techniques and how these conclusions change when the model in question is a DNN. We discuss how DNNs are amenable to new model comparison techniques that allow for stronger conclusions to be made about the computational mechanisms underlying sensory information processing.