Deep learning, computational neuroscience, and cognitive science have overlapping goals related to understanding intelligence such that perception and behaviour can be simulated in computational sys- tems. 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.
Jessica Thompson (Université de Montréal)
More from the Same Authors
2019 : Opening Remarks »
Guillaume Lajoie · Jessica Thompson · Maximilian Puelma Touzel · Eli Shlizerman · Konrad Kording
2019 Workshop: Real Neurons & Hidden Units: future directions at the intersection of neuroscience and AI »
Guillaume Lajoie · Eli Shlizerman · Maximilian Puelma Touzel · Jessica Thompson · Konrad Kording