The Lottery Ticket Hypothesis: On Sparse, Trainable Neural Networks
- Starts: 10:00 am on Thursday, March 25, 2021
- Ends: 11:30 am on Thursday, March 25, 2021
Jonathan Frankle (MIT) will dive into his recently proposed lottery ticket hypothesis: that the dense neural networks we typically train have much smaller subnetworks capable of reaching full accuracy from early in training.
ZOOM LINK: https://bostonu.zoom.us/j/98445398657?pwd=WFVIZ2Y5UUYxY0hLcVhHQUVHK1o5Zz09
- Speakers:
- Jonathan Frankle
- Audience:
- bu
- Fees:
- free
- Registration:
- https://www.bu.edu/cds-faculty/news-events/events/?eid=251477&oid=0
- Contact Organization:
- Faculty of Computing & Data Sciences