HyperENTM: Evolving Scalable Neural Turing Machines through HyperNEAT

TL;DR

This paper introduces HyperENTM, a scalable neural memory model that leverages HyperNEAT encoding to efficiently learn and generalize memory tasks to larger sizes without retraining.

Contribution

It presents a HyperNEAT-based Neural Turing Machine that encodes memory access geometrically, enabling scalable training and transfer to larger memory sizes.

Findings

Networks trained on small memory vectors can be scaled to larger sizes without retraining.

HyperNEAT encoding facilitates generalization to larger memory sizes in memory-augmented neural networks.

Results suggest potential for handling larger, more complex memory tasks in neural networks.

Abstract

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.