Convolutional Residual Memory Networks

Joel Moniz, Christopher Pal

Published 2016-06-16Version 1

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradient problem becomes a key issue. Recent evidence also indicates that convolutional networks could benefit from an interface to explicitly constructed memory mechanisms interacting with a CNN feature processing hierarchy. Correspondingly, we propose and evaluate a memory mechanism enhanced convolutional neural network architecture based on augmenting convolutional residual networks with a long short term memory mechanism. We refer to this as a convolutional residual memory network and we find that this approach can yield state of the art performance on the CIFAR-100 and SVHN benchmarks. This is achieved using a network with more breadth, much less depth and much less overall computation relative to comparable models without the memory mechanism. Our experiments and analysis explore the importance of the memory mechanism, network depth, breadth, and predictive performance.