Thinking Like Transformers RNNs have direct parallels in finite state machines, but Transformers have no such familiar parallel. This paper aims to change that. They propose a computational model for the Transformer in the form of a programming language. https://t.co/OuPBSrS1EJ https://t.co/zYyAcH2zQd
— hardmaru (@hardmaru) Jun 16, 2021
from Twitter https://twitter.com/hardmaru
June 15, 2021 at 11:15PM
via IFTTT
No comments:
Post a Comment