2000 character limit reached
Probabilistic Transformers (2010.15583v3)
Published 15 Oct 2020 in cs.LG and stat.ML
Abstract: We show that Transformers are Maximum Posterior Probability estimators for Mixtures of Gaussian Models. This brings a probabilistic point of view to Transformers and suggests extensions to other probabilistic cases.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.