Think Again Networks and the Delta Loss

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).

redacted experiments on language modeling due to evaluation error

References in corpus (2)

• Regularizing and Optimizing LSTM Language Models
• An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing