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

Released as a article .

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)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-11-15
Version   v1
Language   en ?
arXiv  2111.07898v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: efefbcc9-bccb-43d2-8ced-2d5eb09808f4
API URL: JSON