Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Chaoyue Liu 0001, Libin Zhu, Misha Belkin. Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022. [doi]

This author has not been identified. Look up 'Chaoyue Liu 0001' in GoogleThis author has not been identified. Look up 'Libin Zhu' in GoogleThis author has not been identified. Look up 'Misha Belkin' in Google

runs on WebDSL