MIT News company blog
Neural nets typically contain smaller “subnetworks” that can often learn faster
MIT CSAIL's "Lottery ticket hypothesis" finds that neural networks typically contain smaller subnetworks that can be trained to make equally accurate predictions, and often much more quickly.
- Points
- 128
- HN comments
- 20
- Submissions
- 1
- Cited by
- 0 commenters
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| May 16, 2019 | Neural nets typically contain smaller “subnetworks” that can often learn faster by pizza | 128 | 20 |
