Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
This addresses the problem of forgetting in lifelong learning for AI systems, offering an incremental improvement over existing methods.
The paper tackles catastrophic forgetting in sequential task learning by reparameterizing networks to diagonalize the Fisher Information Matrix, resulting in significantly improved performance over standard Elastic Weight Consolidation on datasets like MNIST and CIFAR-100.
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.