# HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT

arXiv: https://arxiv.org/abs/1710.04748 · HTML: https://mlsanity.com/paper/1710.04748/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2017.

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

- [Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers](https://mlsanity.com/paper/2105.07957/) (2021)

## Abstract (arXiv)

Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large memory sizes and sequence lengths. In this paper we show how access to memory can be encoded geometrically through a HyperNEAT-based Neural Turing Machine (HyperENTM). We demonstrate that using the indirect HyperNEAT encoding allows for training on small memory vectors in a bit-vector copy task and then applying the knowledge gained from such training to speed up training on larger size memory vectors. Additionally, we demonstrate that in some instances, networks trained to copy bit-vectors of size 9 can be scaled to sizes of 1,000 without further training. While the task in this paper is simple, these results could open up the problems amendable to networks with external memories to problems with larger memory vectors and theoretically unbounded memory sizes.