Localizing Catastrophic Forgetting in Neural Networks

Bin Yang; Felix Wiewel

arxiv: 1906.02568 · v1 · pith:6DMUB5ZBnew · submitted 2019-06-06 · 💻 cs.LG · cs.AI· cs.NE· stat.ML

Localizing Catastrophic Forgetting in Neural Networks

Felix Wiewel , Bin Yang This is my paper

classification 💻 cs.LG cs.AIcs.NEstat.ML

keywords catastrophicforgettingannsmethodnetworksneuralphenomenonanalyze

0 comments

read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning
cs.NE 2023-05 unverdicted novelty 6.0

An ART-based topological clustering algorithm estimates vigilance and edge deletion thresholds automatically using determinantal point process and edge age for parameter-free continual learning.