Random deep neural networks are biased towards simple functions - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Giacomo De Palma, Bobak Toussi Kiani, Seth Lloyd. Random deep neural networks are biased towards simple functions. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 1962-1974, 2019. [doi]

This author has not been identified. Look up 'Giacomo De Palma' in GoogleThis author has not been identified. Look up 'Bobak Toussi Kiani' in GoogleThis author has not been identified. Look up 'Seth Lloyd' in Google

runs on WebDSL