# Overcoming catastrophic forgetting in neural networks

“Overcoming catastrophic forgetting in neural networks” (2017), by James Kirkpatrick et al. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.

- Authors: James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska‐Barwińska et al.
- Published: March 14, 2017
- Field: Computer Science
- DOI: https://doi.org/10.1073/pnas.1611835114
- Free PDF: https://arxiv.org/pdf/1612.00796

## Abstract

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been 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 that 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 a hand-written digit dataset and by learning several Atari 2600 games sequentially.

Canonical page: https://nerdi.pages.dev/paper/W2560647685
Read three real papers a day in Nerdi (iPhone): https://apps.apple.com/app/apple-store/id6813826387?pt=128757794&ct=web-paper&mt=8