Using Stigmergy to Incorporate the Time into Artificial Neural Networks
A current research trend in neurocomputing involves the design of novel artificial neural networks incorporating the concept of time into their operating model. In this paper, a novel architecture that employs stigmergy is proposed. Computational stigmergy is used to dynamically increase (or decrease) the strength of a connection, or the activation level, of an artificial neuron when stimulated (or released). This study lays down a basic framework for the derivation of a stigmergic NN with a related training algorithm. To show its potential, some pilot experiments have been reported. The XOR problem is solved by using only one single stigmergic neuron with one input and one output. A static NN, a stigmergic NN, a recurrent NN and a long short-term memory NN have been trained to solve the MNIST digits recognition benchmark.
KeywordsArtificial neural networks Stigmergy Deep learning Supervised learning
This work was partially carried out in the framework of the SCIADRO project, co-funded by the Tuscany Region (Italy) under the Regional Implementation Programme for Underutilized Areas Fund (PAR FAS 2007-2013) and the Research Facilitation Fund (FAR) of the Ministry of Education, University and Research (MIUR).
This research was supported in part by the PRA 2018_81 project entitled “Wearable sensor systems: personalized analysis and data security in healthcare” funded by the University of Pisa.
- 8.Cimino, M.G.C.A., Lazzeri, A., Vaglini, G.: Improving the analysis of context-aware information via marker-based stigmergy and differential evolution. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015. LNCS (LNAI), vol. 9120, pp. 341–352. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-19369-4_31CrossRefGoogle Scholar
- 9.Alfeo, A.L., Cimino, M.G., Vaglini, G.: Measuring physical activity of older adults via smartwatch and stigmergic receptive fields. In: Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM), pp. 724–730. Scitepress (2017)Google Scholar
- 11.LeCun, Y., Cortes, C., Burges, C.J.C.: The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/. Accessed 03 Sept 2018
- 12.Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, pp. 1–13 (2015)Google Scholar
- 13.PyTorch, Tensors and Dynamic neural networks in Python with strong GPU acceleration. https://pytorch.org. Accessed 14 Sept 2018
- 14.GitHub platform. https://github.com/galatolofederico/mike2018. Accessed 14 Sept 2018