HackerPapers

arXiv:1612.00796cs.LG

Overcoming catastrophic forgetting in neural networks

James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell

Abstract

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks which they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on the MNIST hand written digit dataset and by learning several Atari 2600 games sequentially.

arXiv comments
Journal reference
DOI
doi:10.1073/pnas.1611835114
Subjects
cs.LGMachine Learning cs.AIArtificial Intelligence stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Sep 2017 to Jun 2025. Found in 1 HN submission from Dec 2016 to Dec 2016. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Self-Adapting Language Models 1 comment

    • AGI likely a combination of these two papers + something new likely along the lines of distillation. 1. Preventing collapse -> model gets "full" https://arxiv.org/pdf/1612.00796 2. Forgetting causes better generalization https://arxiv.org/abs/2307.01163 3. Unknow paper that…

      johnsmith1840View on HNParent context

  2. Is AI Riding a One-Trick Pony? 1 comment

    • Yes there are still lots of people trying to take Hinton and other's old approach and rediscovering the many ways it lacks for general intelligence. However, it is also the case that people are making a shitton of progress in overcoming those problems, both while keeping some of…

      ilakshView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.