Research Article

Application of Predictive Coding in Neuroevolution

by  Heman Mohabeer, K.M. Sunjiv Soyjaudah
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 114 - Issue 2
Published: March 2015
Authors: Heman Mohabeer, K.M. Sunjiv Soyjaudah
10.5120/19953-1782
PDF

Heman Mohabeer, K.M. Sunjiv Soyjaudah . Application of Predictive Coding in Neuroevolution. International Journal of Computer Applications. 114, 2 (March 2015), 41-47. DOI=10.5120/19953-1782

                        @article{ 10.5120/19953-1782,
                        author  = { Heman Mohabeer,K.M. Sunjiv Soyjaudah },
                        title   = { Application of Predictive Coding in Neuroevolution },
                        journal = { International Journal of Computer Applications },
                        year    = { 2015 },
                        volume  = { 114 },
                        number  = { 2 },
                        pages   = { 41-47 },
                        doi     = { 10.5120/19953-1782 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2015
                        %A Heman Mohabeer
                        %A K.M. Sunjiv Soyjaudah
                        %T Application of Predictive Coding in Neuroevolution%T 
                        %J International Journal of Computer Applications
                        %V 114
                        %N 2
                        %P 41-47
                        %R 10.5120/19953-1782
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper presents promising results achieved by applying a new coding scheme based on predictive coding to neuroevolution. The technique proposed exploits the ability of a bit, which contains sufficient information, to represent its neighboring bits. In this way, a single bit represents not only its own information, but also that of its neighborhood. Moreover, whenever there is a change in bit representation, it is determined by a threshold value that determine the point at which the change in information is significant. The main contributions of this work are the following: (i) the ratio of the number of bits to the amount of information content is reduced; (ii) the complexity of the overall system is reduced as there is lesser amount of bit to process; (iii) Finally, we successfully apply the coding scheme to NEAT, which is used as a biometric classifier for the authentication of keystroke dynamics

References
  • Mohabeer H, Soyjaudah K. M. S 2012 Application of Predictive Coding in the Evolution of Artificial Neural Network. IEEE 3rd International conference on Cognitive Infocommunication (CogInfoCom), 775-780.
  • Coates A, Ng A. Y 2011 The importance of Encoding versus Training with Sparse Coding and Vector Quantization. Proc. Of the 28th International Conference on Machine Learning, Bellevue, 921- 928.
  • Ahmadian K, Gavrilona M 2012 Chaotic Neural Network for Biometric Pattern Recognition. Advances in Artificial Intelligence, Vol. 11.
  • Rogers T. T, McClelland J. L 2003 Semantic Cognition: A Parallel Distributed Processing Approach. MIT press.
  • Wilke Stephan D 2001 Neural Coding of Dynamic Stimuli. Proc. of the International Conference on Artificial Neural Networks. 1081-1086.
  • Spratling M. W, Johnson M. H 2004 Neural coding strategies and Mechanisms of Competition. Cognitive System Research, Vol. 5(2), 93-117.
  • Cybento G 1989 Approximation by superposition of a sigmoidal function. Math. Control Signals Systems, 303-314.
  • Ducker D. M, Kerr W. T, Aguirre G. K 2009 Distinguishing Conjoint and Independent Neural Tuning for Stimulus Features with fMRI Adaptation. J. Neurophysiol, Vol. 101(6). 3310-3324.
  • Silva F, Urbano P, Oliviera S, Christensen A. L 2012 odNEAT: An algorithm for Distributed Online, Onboard Evolution of Robot Behaviors. MIT press.
  • Thorpe S. J, 1995 Localized versus distributed representations. In M. A. Arbib (Ed. ) The handbook of brain theory and Neural Networks. Cambridge, MA: MIT press, 549- 552.
  • Page M 2000 Connectionist modelling in psychology: a local manifesto. Behavioral and Brain Sciences. Vol. 23(4), 443-467.
  • Frsiton K, Kiebel S 2009 Cortical Circuits for Perpetual Interference. Neural network. Vol. 22, pp 1093-1104.
  • Brown E. C, Brune M 2001 The Role of Prediction in Social neuroscience. Frontiers in Human Neuroscience.
  • Huang Y, Rao R. P. N 2011 Predictive coding. WIREs cognitive science, vol. 2(5).
  • Bubic A, Cramon D. Y. V, Schubotz R. I 2010 Prediction, Cognition and the Brain. Frontiers in Human Neuroscience. vol. 4 (25).
  • Jehee J. F. M, Ballard D. H 2009 Predictive Feedback can Account for Biphasic Responses in the Lateral Geniculate Nucleus. Computational Biology. Vol. 5(5).
  • Yao X 1999 Evolving Artificial Neural Networks. Proceedings of the IEEE. Vol. 87(9). 1423- 1447.
  • Cybenko G 1989 Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems. Vol. 2(4), 303–314.
  • Radcliff J. D 199 Genetic set recombination and its applications to neural network topology optimization. Neural Computing and Applications. Vol 1(1). Vol. 67-90, DOI: 10. 1007/BF01411376.
  • Stanley K. O, Mikkulainen R 2002 Evolving Neural Network Through Augmented Topologies, Evolutionary Computation. Vol. 10(2).
  • Tao Y et al 2003 Genetic Dissection of Hybrid Incompatibilities between Drosophila and D. Mauritiana II Mapping Hybrid Male Sterility Loci on the third Chromosome, Genetics. Vol. 164, 1399-1418.
  • Gavrilets S, Li H, Vose M. D 2000 Patterns of Parapatric Speciation. Evolution. Vol. 54 (4), 1126-1134.
  • Martin A. P 1999 Increasing genomic complexity by gene duplication and the origin of vertebrates. The American Naturalist. Vol. 154(2), 111–128.
  • Force A. et al 1999 Preservation of duplicate genes by complementary, degenerative mutations. Genetics. Vol. 151, 1531–1545.
  • Lindgren K, Johansson J 2001 Coevolution of strategies in n-person prisoner's dilemma. In Crutchfield, J. , and Schuster, P. , editors, Evolutionary Dynamics - Exploring the Interplay of Selection, Neutrality, Accident, and Function. Reading, MA: Addison-Wesley.
  • Jain A. K, Nandakumar K, Ross A 2005 Score Normalization in Multimodal Biometric Systems. Pattern Recognition. Vol. 38(12), 2270- 2285.
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

NEAT Predictive Coding Biometric coding scheme

Powered by PhDFocusTM