# Think Again Networks and the Delta Loss

arXiv: https://arxiv.org/abs/1904.11816 · HTML: https://mlsanity.com/paper/1904.11816/

## Key facts

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

## Built on by (most cited first, 1 of 1)

- [NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks](https://mlsanity.com/paper/2402.15393/) (2024)

## 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).