Continuous Reinforced Snap-Drift Learning in a Neural Architecture for Proxylet Selection in Active Computer Networks

Article


Palmer-Brown, Dominic and Lee, S. 2005. Continuous Reinforced Snap-Drift Learning in a Neural Architecture for Proxylet Selection in Active Computer Networks. International Journal on Simulation: Systems, Science and Technology. 6 (9), pp. 11-21.
AuthorsPalmer-Brown, Dominic and Lee, S.
Abstract

A new continuous learning method is used to optimise the selection of services in response to user requests
in an active computer network simulation environment. The learning is an enhanced version of the ‘snap-drift’
algorithm, which employs the complementary concepts of fast, minimalist (snap) learning and slower drift (towards the
input patterns) learning, in a non-stationary environment where new patterns arrive continually. Snap is based on
Adaptive Resonance Theory, and drift on Learning Vector Quantisation. The new algorithm swaps its learning style
between these two self-organisational modes when declining performance is detected, but maintains the same learning
mode during episodes of improved performance. Performance updates occur at the end of each epoch. Reinforcement is
implemented by enabling learning on any given pattern with a probability that increases linearly with declining
performance. This method, which is capable of rapid re-learning, is used in the design of a modular neural network
system: Performance-guided Adaptive Resonance Theory (P-ART). Simulations involving a requirement to
continuously adapt to make appropirate decisions within a BT active computer network environment, demonstrate the
learning is stable, and able to discover alternative solutions in rapid response to new performance requirements or
significant changes in the stream of input patterns.

KeywordsComputational Intelligence; Artificial Neural Networks; Category Learning; Reinforcement Learning
JournalInternational Journal on Simulation: Systems, Science and Technology
Journal citation6 (9), pp. 11-21
ISSN1473-804x
1473-8031
Year2005
Publisher's version
License
CC BY-ND
Web address (URL)http://ducati.doc.ntu.ac.uk/uksim/journal/Vol-6/No.9/Paper2.pdf
http://hdl.handle.net/10552/770
Publication dates
PrintAug 2005
Publication process dates
Deposited29 Apr 2010
Additional information

Citation:
Palmer-Brown, D.; Lee, S.W. (2005). “Continuous Reinforced Snap-Drift Learning in a Neural Architecture for Proxylet Selection in Active Computer Networks.” International Journal on Simulation: Systems, Science and Technology, 6 (9) 11-21..

Permalink -

https://repository.uel.ac.uk/item/867z3

  • 5
    total views
  • 7
    total downloads
  • 1
    views this month
  • 1
    downloads this month

Related outputs

Activities of daily life recognition using process representation modelling to support intention analysis
Naeem, U., Bashroush, R., Anthony, Richard, Azam, Muhammad Awais, Tawil, Abdel Rahman, Lee, S. and Mou-Ling, Dennis 2015. Activities of daily life recognition using process representation modelling to support intention analysis. International Journal of Pervasive Computing and Communications. 11 (3), pp. 347-371.
Direct state feedback optimal control of a double integrator plant implemented by an artificial neural network
Matieni, Xavier, Dodds, Stephen J. and Lee, S. 2011. Direct state feedback optimal control of a double integrator plant implemented by an artificial neural network. Advances in Computing and Technology. University of East London, London Jan 2011 London University of East London, School of Architecture Computing and Engineering.
Closed-loop control using a backpropagation algorithm: a practicable approach for energy loss minimisation in electrical drives.
Matieni, Xavier, Dodds, Stephen J. and Lee, S. 2010. Closed-loop control using a backpropagation algorithm: a practicable approach for energy loss minimisation in electrical drives. Proceedings of Advances in Computing and Technology, (AC&T) The School of Computing and Technology 5th Annual Conference, University of East London, pp. 72-78
Question response grouping for online diagnostic feedback
Lee, S., Palmer-Brown, Dominic, Draganova, Chrisina, Preston, David and Kretsis, Mike 2009. Question response grouping for online diagnostic feedback. Proceedings of Advances in Computing and Technology. (AC&T) The School of Computing and Technology 4th Annual Conference University of East London pp. 68-76
Automated updating of road network databases: road segment grouping using snap-drift neural network
Ekpenyong, Frank, Brimicombe, Allan J., Palmer-Brown, Dominic, Li, Yang and Lee, S. 2007. Automated updating of road network databases: road segment grouping using snap-drift neural network. Proceedings of Advances in Computing and Technology. (AC&T) The School of Computing and Technology 2nd Annual Conference University of East London pp. 160-167
An assessment of neural network algorithms that could aid SME survival
Walcott, Terry H., Palmer-Brown, Dominic, Williams, Godfried, Mouratidis, Haralambos and Lee, S. 2007. An assessment of neural network algorithms that could aid SME survival. Proceedings of Advances in Computing and Technology. (AC&T) The School of Computing and Technology 2nd Annual Conference University of East London pp. 120-127
Feature discovery using snap-drift neural networks
Lee, S. and Palmer-Brown, Dominic 2007. Feature discovery using snap-drift neural networks. Proceedings of Advances in Computing and Technology. (AC&T) The School of Computing and Technology 2nd Annual Conference University of East London pp. 61-70
Modal Learning in a Neural Network
Lee, S. and Palmer-Brown, Dominic 2006. Modal Learning in a Neural Network. Proceedings of the AC&T, pp. 42-47
Performance-guided Neural Network for Self-Organising Network Management
Lee, S., Palmer-Brown, Dominic, Tepper, Jonathan and Roadknight, Christopher 2002. Performance-guided Neural Network for Self-Organising Network Management. Proceedings of London Communication Symposium (LCS'2002) University College London, London, UK, 9th – 10th September, pp. 269 - 272
Fast Learning Neural Nets with Adaptive Learning Styles
Palmer-Brown, Dominic, Lee, S., Tepper, Jonathan and Roadknight, Chris 2003. Fast Learning Neural Nets with Adaptive Learning Styles.
Snap-Drift: Real-time, Performance-guided Learning
Lee, S., Palmer-Brown, Dominic, Tepper, Jonathan and Roadknight, Christopher 2003. Snap-Drift: Real-time, Performance-guided Learning.
The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks
Palmer-Brown, Dominic and Lee, S. 2005. The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks. International Journal on Simulation: Systems, Science and Technology. 6 (9), pp. 22-32.
Phonetic Feature Discovery in Speech using Snap-Drift
Lee, S. and Palmer-Brown, Dominic 2006. Phonetic Feature Discovery in Speech using Snap-Drift.
Early SME Market Prediction using USDNN
Walcott, Terry H., Palmer-Brown, Dominic and Lee, S. 2008. Early SME Market Prediction using USDNN. in: Proceedings of the International Conference of Computational Intelligence and Intelligent Systems (ICCIIS'2008) International Association of Engineers.
A Neural Network Approach for Intrusion Detection Systems
Beqiri, Elidon, Lee, S. and Draganova, Chrisina 2010. A Neural Network Approach for Intrusion Detection Systems. 5th Conference in Advances in Computing and Technology (London, United Kingdom, 27th Jan), pp. 209 -217
Diagnostic Feedback by Snap-drift Question Response Grouping
Lee, S., Palmer-Brown, Dominic and Draganova, Chrisina 2008. Diagnostic Feedback by Snap-drift Question Response Grouping. in: Proceedings of 9th WSEAS International Conference on Neural Networks (NN'08) Stevens Point (WI), USA World Scientific and Engineering Academy and Society. pp. 208-214
Modal Learning Neural Networks
Palmer-Brown, Dominic, Lee, S., Draganova, Chrisina and Kang, Miao 2009. Modal Learning Neural Networks.
Snap-Drift Neural Network for Selecting Student Feedback
Palmer-Brown, Dominic, Draganova, Chrisina and Lee, S. 2009. Snap-Drift Neural Network for Selecting Student Feedback. International Joint Conference on Neural Networks, IJCNN 2009. Atlanta, Georgia, USA 14 - 19 Jun 2009 IEEE.