Evolving spiking neural networks for temporal pattern recognition in the presence of noise

Ahmed Abdelmotaleb; N. Davey; M. Schilstra; Volker Steuber; Borys Wrobel

doi:10.7551/978-0-262-32621-6-ch157

Evolving spiking neural networks for temporal pattern recognition in the presence of noise

Ahmed Abdelmotaleb, N. Davey, M. Schilstra, Volker Steuber, Borys Wrobel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

161 Downloads (Pure)

Abstract

Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear.
In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial life platform
that encodes the topology of the network (and the weights of connections) in a fashion inspired by the encoding of gene regulatory networks in biological genomes. The number of computational nodes or connections is not limited in GReaNs, but here we limit the size of the networks to analyze the functioning of the networks and the effect of network size on the evolvability of robustness to noise. Our results show that even very small networks of spiking neurons can perform temporal pattern recognition in the presence of input noise

Original language	English
Title of host publication	Artificial Life 2014
Subtitle of host publication	Procs of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems
Editors	Hiroki Sayama
Publisher	MIT Press
Pages	965-972
DOIs	https://doi.org/10.7551/978-0-262-32621-6-ch157
Publication status	Published - 2014
Event	Artificial Life 2014 - New York, United States Duration: 30 Jul 2014 → …

Conference

Conference	Artificial Life 2014
Country/Territory	United States
City	New York
Period	30/07/14 → …

Access to Document

10.7551/978-0-262-32621-6-ch157

906898
Creative Commons - Attribution-NonCommercial-NoDerivs 3.0 United States
Final published version, 899 KB

http://mitpress.mit.edu/sites/default/files/titles/free_download/9780262326216_Artificial_Life_2014.pdf

Cite this

Abdelmotaleb, A., Davey, N., Schilstra, M., Steuber, V., & Wrobel, B. (2014). Evolving spiking neural networks for temporal pattern recognition in the presence of noise. In H. Sayama (Ed.), Artificial Life 2014: Procs of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems (pp. 965-972). MIT Press. https://doi.org/10.7551/978-0-262-32621-6-ch157

@inproceedings{02574378ed58465ba4d1e489cd0bef75,

title = "Evolving spiking neural networks for temporal pattern recognition in the presence of noise",

abstract = "Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear. In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial life platform that encodes the topology of the network (and the weights of connections) in a fashion inspired by the encoding of gene regulatory networks in biological genomes. The number of computational nodes or connections is not limited in GReaNs, but here we limit the size of the networks to analyze the functioning of the networks and the effect of network size on the evolvability of robustness to noise. Our results show that even very small networks of spiking neurons can perform temporal pattern recognition in the presence of input noise",

author = "Ahmed Abdelmotaleb and N. Davey and M. Schilstra and Volker Steuber and Borys Wrobel",

note = "Creative Commons - Attribution-NonCommercial-NoDerivs 3.0 United States; Artificial Life 2014 ; Conference date: 30-07-2014",

year = "2014",

doi = "10.7551/978-0-262-32621-6-ch157",

language = "English",

pages = "965--972",

editor = "Hiroki Sayama",

booktitle = "Artificial Life 2014",

publisher = "MIT Press",

address = "United States",

}

Abdelmotaleb, A, Davey, N, Schilstra, M, Steuber, V & Wrobel, B 2014, Evolving spiking neural networks for temporal pattern recognition in the presence of noise. in H Sayama (ed.), Artificial Life 2014: Procs of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems. MIT Press, pp. 965-972, Artificial Life 2014, New York, United States, 30/07/14. https://doi.org/10.7551/978-0-262-32621-6-ch157

Evolving spiking neural networks for temporal pattern recognition in the presence of noise. / Abdelmotaleb, Ahmed; Davey, N.; Schilstra, M. et al.
Artificial Life 2014: Procs of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems. ed. / Hiroki Sayama. MIT Press, 2014. p. 965-972.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Evolving spiking neural networks for temporal pattern recognition in the presence of noise

AU - Abdelmotaleb, Ahmed

AU - Davey, N.

AU - Schilstra, M.

AU - Steuber, Volker

AU - Wrobel, Borys

N1 - Creative Commons - Attribution-NonCommercial-NoDerivs 3.0 United States

PY - 2014

Y1 - 2014

N2 - Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear. In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial life platform that encodes the topology of the network (and the weights of connections) in a fashion inspired by the encoding of gene regulatory networks in biological genomes. The number of computational nodes or connections is not limited in GReaNs, but here we limit the size of the networks to analyze the functioning of the networks and the effect of network size on the evolvability of robustness to noise. Our results show that even very small networks of spiking neurons can perform temporal pattern recognition in the presence of input noise

AB - Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear. In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial life platform that encodes the topology of the network (and the weights of connections) in a fashion inspired by the encoding of gene regulatory networks in biological genomes. The number of computational nodes or connections is not limited in GReaNs, but here we limit the size of the networks to analyze the functioning of the networks and the effect of network size on the evolvability of robustness to noise. Our results show that even very small networks of spiking neurons can perform temporal pattern recognition in the presence of input noise

U2 - 10.7551/978-0-262-32621-6-ch157

DO - 10.7551/978-0-262-32621-6-ch157

M3 - Conference contribution

SP - 965

EP - 972

BT - Artificial Life 2014

A2 - Sayama, Hiroki

PB - MIT Press

T2 - Artificial Life 2014

Y2 - 30 July 2014

ER -

Evolving spiking neural networks for temporal pattern recognition in the presence of noise

Abstract

Conference

Access to Document

Fingerprint

Cite this