Abstract
An artificial neural network is modeled by weighting between different neurons to form synaptic connections. The nonlinear line attractor (NLA) models the weighting architecture by a polynomial weight set, which provides stronger connections between neurons. With the connections between neurons, we desired neuron weighting based on proximity using a Gaussian weighting strategy of the neurons that should reduce computational times significantly. Instead of using proximity to the neurons, it is found that utilizing the error found from estimating the output neurons to weight the connections between the neurons would provide the best results. The polynomial weights that are trained into the neural network will be reduced using a nonlinear dimensionality reduction which preserves the locality of the weights, since the weights are Gaussian weighted. A distance measure is then used to compare the test and training data. From testing the algorithm, it is observed that the proposed weighted NLA algorithm provides better recognition than both the GNLA algorithm and the original NLA algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. sci. 79, 2554–2558 (1982)
Lewis, J.E., Glass, L.: Steady states, limit cycles, and chaos in models of complex biological networks. Int. J. Bifurcat. Chaos 1, 477–483 (1991)
Zhang, K.: Representation of spatial orientation by the intrinsic dynamics of the head-direction cell ensemble: a theory. J. Neurosci. 16, 2112–2126 (1996)
Tononi, G., Sporns, O., Edelman, G.M.: Measures of degeneracy and redundancy in biological networks. Proc. Nat. Acad. Sci. 96, 3257–3262 (1999)
Guido, W., Spear, P., Tong, L.: Functional compensation in the lateral suprasylvian visual area following bilateral visual cortex damage in kittens. Exp. Brain Res. 83, 219–224 (1990)
Happel, B.L., Murre, J.M.: Design and evolution of modular neural network architectures. Neural Netw. 7, 985–1004 (1994)
Gottumukkal, R., Asari, V.K.: An improved face recognition technique based on modular PCA approach. Pattern Recogn. Lett. 25, 429–436 (2004)
Gomi, H., Kawato, M.: Recognition of manipulated objects by motor learning with modular architecture networks. Neural Netw. 6, 485–497 (1993)
Auda, G., Kamel, M.: Cmnn: cooperative modular neural networks for pattern recognition. Pattern Recogn. Lett. 18, 1391–1398 (1997)
Seow, M.-J., Asari, V.K.: Recurrent network as a nonlinear line attractor for skin color association. In: Yin, F.-L., Wang, J., Guo, C. (eds.) ISNN 2004. LNCS, vol. 3173, pp. 870–875. Springer, Heidelberg (2004). doi:10.1007/978-3-540-28647-9_143
Seow, M.J., Asari, V.K.: Recurrent neural network as a linear attractor for pattern association. IEEE Trans. Neural Netw. 17, 246–250 (2006)
Seow, M.J., Alex, A.T., Asari, V.K.: Learning embedded lines of attraction by self organization for pose and expression invariant face recognition. Opt. Eng. 51, 107201 (2012)
Golub, G.H., Reinsch, C.: Singular value decomposition and least squares solutions. Numer. Math. 14, 403–420 (1970)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Aspiras, T.H., Asari, V.K., Sakla, W. (2017). Weighted Nonlinear Line Attractor for Complex Manifold Learning. In: Merelo, J.J., et al. Computational Intelligence. IJCCI 2015. Studies in Computational Intelligence, vol 669. Springer, Cham. https://doi.org/10.1007/978-3-319-48506-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-48506-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48504-1
Online ISBN: 978-3-319-48506-5
eBook Packages: EngineeringEngineering (R0)