Title | Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex |
Publication Type | CBMM Memo |
Year of Publication | 2016 |
Authors | Liao Q., Poggio T. |
Abstract | 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. |
URL | https://cbmm.mit.edu/sites/default/files/publications/CBMM%20Memo%20047_arxiv1604.03640v1.pdf |
Citation Key | 223 |
CBMM Memo No.:
47