PT Unknown AU Xialei Liu Marc Masana Luis Herranz Joost Van de Weijer Antonio Lopez Andrew Bagdanov TI Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting BT 24th International Conference on Pattern Recognition PY 2018 BP 2262 EP 2268 DI 10.1109/ICPR.2018.8545895 AB 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 ofa 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 andStanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to the state-of-the-art in lifelong learning without forgetting. ER