RT Journal Article
SR Electronic
T1 Reset Networks: Emergent Topography by Composition of Convolutional Neural Networks
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.11.19.469308
DO 10.1101/2021.11.19.469308
A1 Hannagan, T.
YR 2021
UL http://biorxiv.org/content/early/2021/12/01/2021.11.19.469308.abstract
AB We introduce Reset networks, which are compositions of several neural networks - typically several levels of CNNs - where outputs at one level are gathered and reshaped into a spatial input for the next level. We demonstrate that Reset networks exhibit emergent topographic organization for numbers, as well as for visual categories taken from CIFAR-100. We outline the implications of this model for theories of the cortex and developmental neuroscience.Competing Interest StatementThe authors have declared no competing interest.