Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems

Subhabrata Dutta, Tanya Gautam, Soumen Chakrabarti, Tanmoy Chakraborty 0002. Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems. In Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pages 5531-5544, 2021. [doi]

Abstract

Abstract is missing.