Using Stigmergy as a Computational Memory in the Design of Recurrent Neural Networks

Federico Galatolo, Mario Cimino, Gigliola Vaglini

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).

Download


Paper Citation


in Harvard Style

Galatolo F., Cimino M. and Vaglini G. (2019). Using Stigmergy as a Computational Memory in the Design of Recurrent Neural Networks.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 830-836. DOI: 10.5220/0007581508300836


in Bibtex Style

@conference{icpram19,
author={Federico Galatolo and Mario Cimino and Gigliola Vaglini},
title={Using Stigmergy as a Computational Memory in the Design of Recurrent Neural Networks},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={830-836},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007581508300836},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Using Stigmergy as a Computational Memory in the Design of Recurrent Neural Networks
SN - 978-989-758-351-3
AU - Galatolo F.
AU - Cimino M.
AU - Vaglini G.
PY - 2019
SP - 830
EP - 836
DO - 10.5220/0007581508300836