Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results
Name
CBMM-Memo-093.pdf
Size
2.99 MB
Format
Adobe PDF
Checksum (MD5)
c825ac7b7752e2425df85c925f495a93
Author(s)
Arend, Luke
Han, Yena
Schrimpf, Martin
Bashivan, Pouya
Kar, Kohitij
Poggio, Tomaso
DiCarlo, James J.
Boix, Xavier
Date Issued
November 2, 2018
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo Series;093
Abstract
Deep neural networks have been shown to predict neural responses in higher visual cortex. The mapping from the model to a neuron in the brain occurs through a linear combination of many units in the model, leaving open the question of whether there also exists a correspondence at the level of individual neurons. Here we show that there exist many one-to-one mappings between single units in a deep neural network model and neurons in the brain. We show that this correspondence at the single- unit level is ubiquitous among state-of-the-art deep neural networks, and grows more pronounced for models with higher performance on a large-scale visual recognition task. Comparing matched populations—in the brain and in a model—we demonstrate a further correspondence at the level of the population code: stimulus category can be partially decoded from real neural responses using a classifier trained purely on a matched population of artificial units in a model. This provides a new point of investigation for phenomena which require fine-grained mappings between deep neural networks and the brain.
Persistent DSpace Link
