If deep learning is the answer, what is the question?

By Andrew M. Saxe, Stephanie Nelli, Christopher Summerfield. 2020

325 citations recorded by the source corpus.

Subfields: Biophysics, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Cognitive Neuroscience

Citations in the corpus

Orthogonal representations for robust context-dependent task performance in brains and neural networks (2022, positive): “The first is to formalize solutions to the learning of a canonical context-dependent classification paradigm using a feedforward connectionist (or ‘‘deep learning’’) framework (Richards et al., Neuron 110, 1–13, April 6, 2022 9 2019; Saxe et al., 2021).”
Brains and algorithms partially converge in natural language processing (2022, methodology): “Following a recent methodology 33,42,44,46,46,50 – 56 , we address this issue by evaluating whether the activations of a large variety of deep language models linearly map onto those of 102 human brains.”
A connectome of the Drosophila central complex reveals network motifs suitable for flexible navigation and context-dependent action selection (2020, background): “…learning, a broader question concerns the level of understanding that is appropriate or even possible for the function of large and complex neural networks (Gao and Ganguli, 2015; Hasson et al., 2020; Lillicrap and Kording, 2019; Richards et al., 2019; Saxe et al., 2020; Yamins and DiCarlo, 2016).”
PolyRNN: A time-resolved model of polyphonic musical expectations aligned with human brain responses (2025, unknown): “…growing trend in cognitive neurosciences to adopt RNN and Transformer models, which offer a more accurate representation of the neural encoding of perceptual statistical properties (Donhauser & Baillet, 2020; Saxe et al., 2021; Caucheteux & King, 2022; Kanwisher et al., 2023; Arana et al., 2024).”