# Improving the Neural GPU Architecture for Algorithm Learning

arXiv: https://arxiv.org/abs/1702.08727 · HTML: https://mlsanity.com/paper/1702.08727/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2017.

## Built on by (most cited first, 4 of 4)

- [Neural Networks and the Chomsky Hierarchy](https://mlsanity.com/paper/2207.02098/) (2022)
- [End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking](https://mlsanity.com/paper/2202.05826/) (2022)
- [Counting and Algorithmic Generalization with Transformers](https://mlsanity.com/paper/2310.08661/) (2023)
- [Discrete Denoising Diffusion Approach to Integer Factorization](https://mlsanity.com/paper/2309.05295/) (2023)

## Abstract (arXiv)

Algorithm learning is a core problem in artificial intelligence with significant implications on automation level that can be achieved by machines. Recently deep learning methods are emerging for synthesizing an algorithm from its input-output examples, the most successful being the Neural GPU, capable of learning multiplication. We present several improvements to the Neural GPU that substantially reduces training time and improves generalization. We introduce a new technique - hard nonlinearities with saturation costs- that has general applicability. We also introduce a technique of diagonal gates that can be applied to active-memory models. The proposed architecture is the first capable of learning decimal multiplication end-to-end.