mlsanityData to 14 Oct 2026

Think Again Networks and the Delta Loss

arXiv 1904.11816 ↗First posted 26 Apr 2019cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). First posted on arXiv 26 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Taskscited by 1