- Poster presentation
- Open Access
The delayed response network: towards a single layer universal neural network approximator and delay-based learning
- Dinov Martin1Email author and
- Elias Rut2
https://doi.org/10.1186/1471-2202-16-S1-P214
© Martin and Rut 2015
- Published: 18 December 2015
Keywords
- Input Space
- Biological Network
- Time Series Prediction
- Delay Change
- Feedforward Model
A shows three different mathematical formulations implemented. Top equation is original one with which exact bit patterns were learned, as implemented in Scala code. Bottom two equations of A were variations used in more recent work, solving XOR and classifying data. B shows a plot of amount of bit patterns learned by a 2-3-1 DRN architecture as implemented by the top equation in A, showing the effect of the maximum allowed delay per link/connection between two nodes (on x-axis) and the number of bits learned (average and maximum) on the y-axis.
Declarations
Acknowledgements
We thank Dr. Robert Leech for useful discussions and comments.
Authors’ Affiliations
References
- Hornic K: Multilayer Feedforward Networks are Universal Approximators. Neural Networks. 1989, 2 (5): 359-366.View ArticleGoogle Scholar
- Fields RD: Myelination: An Overlooked Mechanism of Synaptic Plasticity?. Neuroscientist. 2005, 11 (6): 528-531.PubMedPubMed CentralView ArticleGoogle Scholar
- Fields RD, Burnstock G: Purinergic signalling in neuron-glia interactions. Nature Reviews Neuroscience. 2006, 7 (6): 423-436.PubMedPubMed CentralView ArticleGoogle Scholar
- Bullmore E, Sporns O: The economy of brain network organization. Nature Reviews Neuroscience. 2012, 336-349. 13Google Scholar
Copyright
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.