Localizing Catastrophic Forgetting in Neural Networks
Machine Learning
2019-06-07 v1 Artificial Intelligence
Neural and Evolutionary Computing
Machine Learning
Abstract
Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for determining the contribution of individual parameters in an ANN to catastrophic forgetting. The method is used to analyze an ANNs response to three different continual learning scenarios.
Cite
@article{arxiv.1906.02568,
title = {Localizing Catastrophic Forgetting in Neural Networks},
author = {Felix Wiewel and Bin Yang},
journal= {arXiv preprint arXiv:1906.02568},
year = {2019}
}