Using stigmergy as a computational memory in the design of recurrent neural networks

TL;DR

This paper introduces a novel Recurrent Neural Network architecture that utilizes stigmergic memory to enhance temporal input encoding, demonstrated through improved performance on the MNIST digit recognition benchmark.

Contribution

The paper proposes a new RNN architecture integrating stigmergic memory, providing a formal framework and demonstrating its effectiveness on benchmark classification tasks.

Findings

Stigmergic memory enhances temporal input encoding in RNNs.

SM-RNN outperforms traditional RNNs on MNIST classification.

The architecture offers a new approach to memory in neural networks.

Abstract

In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activities of deposit/removal. Accordingly, subsequent SM activities tend to reinforce/weaken each other, generating a coherent coordination between the SM activities and the input temporal stimulus. We show that, in a problem of supervised classification, the SM encodes the temporal input in an emergent representational model, by coordinating the deposit, removal and classification activities. This study lays down a basic framework for the derivation of a SM-RNN. A formal ontology of SM is discussed, and the SM-RNN architecture is detailed. To appreciate the computational power of an SM-RNN, comparative NNs have been selected and trained to solve the MNIST handwritten digits recognition benchmark in its two variants: spatial (sequences of bitmap rows) and temporal (sequences of pen strokes).