loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Author: Stylianos Kampakis

Affiliation: University College London, United Kingdom

Keyword(s): Computational Power, Heterogeneous Neurons, Neural Diversity Machines, Computational Neuroscience, Supervised Learning.

Related Ontology Subjects/Areas/Topics: Adaptive Architectures and Mechanisms ; Artificial Intelligence ; Biomedical Engineering ; Biomedical Signal Processing ; Complex Artificial Neural Network Based Systems and Dynamics ; Computational Intelligence ; Computational Neuroscience ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Methodologies and Methods ; Neural Networks ; Neurocomputing ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Sensor Networks ; Signal Processing ; Soft Computing ; Supervised and Unsupervised Learning ; Theory and Methods

Abstract: An idea that has recently appeared in the neural network community is that networks with heterogeneous neurons and non-standard neural behaviors can provide computational advantages. A theoretical investigation of this idea was given by Kampakis (2013) for spiking neurons. In artificial neural networks this idea has been recently researched through Neural Diversity Machines (Maul, 2013). However, this idea has not been tested experimentally for spiking neural networks. This paper provides a first experimental investigation of whether neurons with non-standard behaviors can provide computational advantages. This is done by using a spiking neural network with a biologically realistic neuron model that is tested on a supervised learning task. In the first experiment the network is optimized for the supervised learning task by adjusting the parameters of the neurons in order to adapt the neural behaviors. In the second experiment, the parameter optimization is used in order to improve th e network’s performance after the weights have been trained. The results confirm that neurons with non-standard behaviors can provide computational advantages for a network. Further implications of this study and suggestions for future research are discussed. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 44.192.247.185

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kampakis, S. (2014). Are Non-Standard Neural Behaviors Computationally Relevant?. In Proceedings of the International Conference on Neural Computation Theory and Applications (IJCCI 2014) - NCTA; ISBN 978-989-758-054-3, SciTePress, pages 32-37. DOI: 10.5220/0005030400320037

@conference{ncta14,
author={Stylianos Kampakis.},
title={Are Non-Standard Neural Behaviors Computationally Relevant?},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications (IJCCI 2014) - NCTA},
year={2014},
pages={32-37},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005030400320037},
isbn={978-989-758-054-3},
}

TY - CONF

JO - Proceedings of the International Conference on Neural Computation Theory and Applications (IJCCI 2014) - NCTA
TI - Are Non-Standard Neural Behaviors Computationally Relevant?
SN - 978-989-758-054-3
AU - Kampakis, S.
PY - 2014
SP - 32
EP - 37
DO - 10.5220/0005030400320037
PB - SciTePress