Command Palette
Search for a command to run...
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| continual-learning-on-20newsgroup-10-tasks | EWC | F1 - macro: 0.9180 |
| continual-learning-on-asc-19-tasks | L2 | F1 - macro: 0.5243 |
| continual-learning-on-asc-19-tasks | EWC | F1 - macro: 0.7452 |
| continual-learning-on-dsc-10-tasks | EWC | F1 - macro: 0.6576 |
| continual-learning-on-f-celeba-10-tasks | EWC | Acc: 0.6545 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.