Theory of diffusible messenger and learning in neural networks

Tao Wang, Nitish V Thakor

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Nitric oxide (NO) is a newly discovered neuronal messenger which transmits information in brain by way of diffusion. This phenomenon suggests a non-localized form of learning in computational neural network models. Based on a new dynamical description of single neuron learning, we demonstrate that NO diffusion can speed up the learning as well as reduce noise when a neuron is storing a pattern. Based on this idea we present the theory and application of a competitive learning algorithm that simulates pattern identification and classification in neural networks.

Original languageEnglish (US)
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
PublisherIEEE
Pages1383-1384
Number of pages2
Volume3
StatePublished - 1997
EventProceedings of the 1997 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Chicago, IL, USA
Duration: Oct 30 1997Nov 2 1997

Other

OtherProceedings of the 1997 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityChicago, IL, USA
Period10/30/9711/2/97

Fingerprint

Nitric oxide
Neurons
Nitric Oxide
Neural networks
Learning algorithms
Brain

ASJC Scopus subject areas

  • Bioengineering

Cite this

Wang, T., & Thakor, N. V. (1997). Theory of diffusible messenger and learning in neural networks. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (Vol. 3, pp. 1383-1384). IEEE.

Theory of diffusible messenger and learning in neural networks. / Wang, Tao; Thakor, Nitish V.

Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 3 IEEE, 1997. p. 1383-1384.

Research output: Chapter in Book/Report/Conference proceedingChapter

Wang, T & Thakor, NV 1997, Theory of diffusible messenger and learning in neural networks. in Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. vol. 3, IEEE, pp. 1383-1384, Proceedings of the 1997 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, USA, 10/30/97.
Wang T, Thakor NV. Theory of diffusible messenger and learning in neural networks. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 3. IEEE. 1997. p. 1383-1384
Wang, Tao ; Thakor, Nitish V. / Theory of diffusible messenger and learning in neural networks. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 3 IEEE, 1997. pp. 1383-1384
@inbook{35c8b1b7b4e1442c8c3d5e63c4d09689,
title = "Theory of diffusible messenger and learning in neural networks",
abstract = "Nitric oxide (NO) is a newly discovered neuronal messenger which transmits information in brain by way of diffusion. This phenomenon suggests a non-localized form of learning in computational neural network models. Based on a new dynamical description of single neuron learning, we demonstrate that NO diffusion can speed up the learning as well as reduce noise when a neuron is storing a pattern. Based on this idea we present the theory and application of a competitive learning algorithm that simulates pattern identification and classification in neural networks.",
author = "Tao Wang and Thakor, {Nitish V}",
year = "1997",
language = "English (US)",
volume = "3",
pages = "1383--1384",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
publisher = "IEEE",

}

TY - CHAP

T1 - Theory of diffusible messenger and learning in neural networks

AU - Wang, Tao

AU - Thakor, Nitish V

PY - 1997

Y1 - 1997

N2 - Nitric oxide (NO) is a newly discovered neuronal messenger which transmits information in brain by way of diffusion. This phenomenon suggests a non-localized form of learning in computational neural network models. Based on a new dynamical description of single neuron learning, we demonstrate that NO diffusion can speed up the learning as well as reduce noise when a neuron is storing a pattern. Based on this idea we present the theory and application of a competitive learning algorithm that simulates pattern identification and classification in neural networks.

AB - Nitric oxide (NO) is a newly discovered neuronal messenger which transmits information in brain by way of diffusion. This phenomenon suggests a non-localized form of learning in computational neural network models. Based on a new dynamical description of single neuron learning, we demonstrate that NO diffusion can speed up the learning as well as reduce noise when a neuron is storing a pattern. Based on this idea we present the theory and application of a competitive learning algorithm that simulates pattern identification and classification in neural networks.

UR - http://www.scopus.com/inward/record.url?scp=0031294253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031294253&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0031294253

VL - 3

SP - 1383

EP - 1384

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

PB - IEEE

ER -