Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
Author(s)Liao, Qianli; Poggio, Tomaso
MetadataShow full item record
We discuss relations between Residual Networks (ResNet), Recurrent Neural Networks (RNNs) and the primate visual cortex. We begin with the observation that a shallow RNN is exactly equivalent to a very deep ResNet with weight sharing among the layers. A direct implementation of such a RNN, although having orders of magnitude fewer parameters, leads to a performance similar to the corresponding ResNet. We propose 1) a generalization of both RNN and ResNet architectures and 2) the conjecture that a class of moderately deep RNNs is a biologically-plausible model of the ventral stream in visual cortex. We demonstrate the effectiveness of the architectures by testing them on the CIFAR-10 dataset.
Center for Brains, Minds and Machines (CBMM), arXiv
CBMM Memo Series;047
Residual Networks (ResNet), Recurrent Neural Networks (RNNs), primate visual cortex, CIFAR-10
The following license files are associated with this item: