%0 Generic %D 2016 %T Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex %A Qianli Liao %A Tomaso Poggio %X

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.

%8 04/2016 %1

arXiv:1604.03640

%2

http://hdl.handle.net/1721.1/102238