Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization
release_lu5bgxtpy5b6fnkk3bmxjv4hzy
by
Sushrut Thorat, Giacomo Aldegheri, Tim C. Kietzmann
2021
Abstract
Recurrent neural networks (RNNs) have been shown to perform better than
feedforward architectures in visual object categorization tasks, especially in
challenging conditions such as cluttered images. However, little is known about
the exact computational role of recurrent information flow in these conditions.
Here we test RNNs trained for object categorization on the hypothesis that
recurrence iteratively aids object categorization via the communication of
category-orthogonal auxiliary variables (the location, orientation, and scale
of the object). Using diagnostic linear readouts, we find that: (a) information
about auxiliary variables increases across time in all network layers, (b) this
information is indeed present in the recurrent information flow, and (c) its
manipulation significantly affects task performance. These observations confirm
the hypothesis that category-orthogonal auxiliary variable information is
conveyed through recurrent connectivity and is used to optimize category
inference in cluttered environments.
In text/plain
format
Archived Files and Locations
application/pdf 5.1 MB
file_5i6h763iuzf5pczy353tivs6s4
|
arxiv.org (repository) web.archive.org (webarchive) |
2111.07898v1
access all versions, variants, and formats of this works (eg, pre-prints)