Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
Abstract
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and Stanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to other state-of-the-art in lifelong learning without forgetting.
Keywords
Cite
@article{arxiv.1802.02950,
title = {Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting},
author = {Xialei Liu and Marc Masana and Luis Herranz and Joost Van de Weijer and Antonio M. Lopez and Andrew D. Bagdanov},
journal= {arXiv preprint arXiv:1802.02950},
year = {2018}
}
Comments
Accepted at ICPR'18. First two authors contributed equally