The Random Neural Network and its Learning Process in Cognitive Packet Networks

Peixiang Liu

doi:10.1109/icnc.2013.6817951

The Random Neural Network and its Learning Process in Cognitive Packet Networks

Peixiang Liu

Research output: Contribution to conference › Presentation

3 Scopus citations

Abstract

The Random Neural Network (RNN) is a recurrent neural network in which neurons interact with each other by exchanging excitatory and inhibitory spiking signals. The stochastic excitatory and inhibitory interactions in the network make the RNN an excellent modeling tool for various interacting entities. It has been applied in a number of applications such as optimization, image processing, communication systems, simulation pattern recognition and classification. In this paper, we briefly describe the RNN model and some learning algorithms for RNN. We discuss how the RNN with reinforcement learning was successfully applied to Cognitive Packet Network (CPN) architecture so as to offer users QoS driven packet delivery services. The experiments conducted on a 26-node testbed clearly demonstrated the learning capability of the RNNs in CPN.

Original language	American English
Pages	95-100
Number of pages	6
DOIs	https://doi.org/10.1109/icnc.2013.6817951
State	Published - Jul 1 2013
Event	Proceedings from International Conference on Natural Computation 2013 - Duration: Jul 1 2013 → …

Conference

Conference	Proceedings from International Conference on Natural Computation 2013
Period	7/1/13 → …

ASJC Scopus Subject Areas

General Computer Science
Biomedical Engineering
Computational Mechanics
General Mathematics
General Neuroscience

Keywords

AI
cognitive radio
learning
quality of service
radio networks
recurrent neural nets
telecommunication computing
Cognitive Packet Network
Random Neural Network
Reinforcement Learning

Disciplines

Computer Sciences

Access to Document

10.1109/icnc.2013.6817951

http://dx.doi.org/10.1109/ICNC.2013.6817951

Cite this

@conference{59245167f3344799b88054ba39e67646,

title = "The Random Neural Network and its Learning Process in Cognitive Packet Networks",

abstract = " The Random Neural Network (RNN) is a recurrent neural network in which neurons interact with each other by exchanging excitatory and inhibitory spiking signals. The stochastic excitatory and inhibitory interactions in the network make the RNN an excellent modeling tool for various interacting entities. It has been applied in a number of applications such as optimization, image processing, communication systems, simulation pattern recognition and classification. In this paper, we briefly describe the RNN model and some learning algorithms for RNN. We discuss how the RNN with reinforcement learning was successfully applied to Cognitive Packet Network (CPN) architecture so as to offer users QoS driven packet delivery services. The experiments conducted on a 26-node testbed clearly demonstrated the learning capability of the RNNs in CPN.",

keywords = "AI, cognitive radio, learning, quality of service, radio networks, recurrent neural nets, telecommunication computing, Cognitive Packet Network, Random Neural Network, Reinforcement Learning",

author = "Peixiang Liu",

year = "2013",

month = jul,

day = "1",

doi = "10.1109/icnc.2013.6817951",

language = "American English",

pages = "95--100",

note = "Proceedings from International Conference on Natural Computation 2013 ; Conference date: 01-07-2013",

}

TY - CONF

T1 - The Random Neural Network and its Learning Process in Cognitive Packet Networks

AU - Liu, Peixiang

PY - 2013/7/1

Y1 - 2013/7/1

N2 - The Random Neural Network (RNN) is a recurrent neural network in which neurons interact with each other by exchanging excitatory and inhibitory spiking signals. The stochastic excitatory and inhibitory interactions in the network make the RNN an excellent modeling tool for various interacting entities. It has been applied in a number of applications such as optimization, image processing, communication systems, simulation pattern recognition and classification. In this paper, we briefly describe the RNN model and some learning algorithms for RNN. We discuss how the RNN with reinforcement learning was successfully applied to Cognitive Packet Network (CPN) architecture so as to offer users QoS driven packet delivery services. The experiments conducted on a 26-node testbed clearly demonstrated the learning capability of the RNNs in CPN.

AB - The Random Neural Network (RNN) is a recurrent neural network in which neurons interact with each other by exchanging excitatory and inhibitory spiking signals. The stochastic excitatory and inhibitory interactions in the network make the RNN an excellent modeling tool for various interacting entities. It has been applied in a number of applications such as optimization, image processing, communication systems, simulation pattern recognition and classification. In this paper, we briefly describe the RNN model and some learning algorithms for RNN. We discuss how the RNN with reinforcement learning was successfully applied to Cognitive Packet Network (CPN) architecture so as to offer users QoS driven packet delivery services. The experiments conducted on a 26-node testbed clearly demonstrated the learning capability of the RNNs in CPN.

KW - AI

KW - cognitive radio

KW - learning

KW - quality of service

KW - radio networks

KW - recurrent neural nets

KW - telecommunication computing

KW - Cognitive Packet Network

KW - Random Neural Network

KW - Reinforcement Learning

UR - https://nsuworks.nova.edu/gscis_facpres/72

UR - http://dx.doi.org/10.1109/ICNC.2013.6817951

U2 - 10.1109/icnc.2013.6817951

DO - 10.1109/icnc.2013.6817951

M3 - Presentation

SP - 95

EP - 100

T2 - Proceedings from International Conference on Natural Computation 2013

Y2 - 1 July 2013

ER -

The Random Neural Network and its Learning Process in Cognitive Packet Networks

Abstract

Conference

ASJC Scopus Subject Areas

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this