Think Again Networks and the Delta Loss
classification
💻 cs.CL
cs.LG
keywords
networksthinkabstractionappliedcalleddeltafunctionintroduces
read the original abstract
This short paper introduces an abstraction called Think Again Networks (ThinkNet) which can be applied to any state-dependent function (such as a recurrent neural network).
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.