DeepMind Blog company blog
Enabling Continual Learning in Neural Networks
Computer programs that learn to perform tasks also typically forget them very quickly. We show that the learning rule can be modified so that a program can remember old tasks when learning a new one. This is an important step towards more intelligent programs that are able to learn progressively and adaptively.
- Points
- 152
- HN comments
- 19
- Submissions
- 1
- Cited by
- 4 commenters
AI & Machine LearningSoftware Engineering2017
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Mar 14, 2017 | Enabling Continual Learning in Neural Networks by interconnector | 152 | 19 |
Cited in comments
Linked from 4 Hacker News comments by 4 different people, from Mar 2017 to May 2017.
Most recent:
