Reset Networks: Emergent Topography in Networks of Convolutional Neural Networks
Keyword(s):
We introduce Reset networks, which are compositions of several neural networks - typically several levels of CNNs - where possibly non-spatial outputs at one level are reshaped into spatial inputs 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.
2020 ◽
Vol 2020
(10)
◽
pp. 28-1-28-7
◽
2017 ◽
Vol 2017
(25)
◽
pp. 48-57