Abstract
A temporal variant of Foldiak's first model with lateral inhibitory synaptic weights is proposed. The usual symmetric scalar values of the lateral weights are replaced with data driven asymmetric memory based lateral weights, which take the form of Finite Impulse Response (FIR) coefficients. Linear anti-Hebbian learning, as defined by Foldiak (IEEE/INNS International Joint Conference on Neural Networks, 1989) and Matsuoka et al. (Neural Networks, Vol. 8, pp. 411–419, 1995), is employed in the self-organisation of the network weights. The temporal anti-Hebbian learning, when applied to the separation of convolved mixtures of signals, causes the network weights to converge to the truncated FIR filter coefficients of the unmixing transfer function and so recover the original signals. Simulation results are presented for separating two natural speech sources convolved and mixed by a priori unknown direct and cross-coupled transfer functions. We compare temporal anti-Hebbian learning with information maximisation learning when applied to the blind separation of convolved sources.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
P. Foldiak, “Adaptive network for optimal linear feature extraction”, IEEE/INNS International Joint Conference on Neural Networks, Vol. 1, pp. 401–405, Washington DC: Institute of Electrical and Electronics Engineers, San Diego, 1989.
H.B. Barlow, “A theory about the functional role and synaptic mechanism of visual after-effects”, in C.B. Blakemore (eds) Vision: Coding and Efficiency, pp. 363–375, Cambridge University Press: Cambridge, UK, 1990.
C. Jutten and J. Herault, “Blind separation of sources, part 1: an adaptive algorithm based on neuromimetic architecture”, Signal Processing, Vol. 24, pp. 1–10, 1991.
A. Cichocki, C. Kasprzak and S. Amari, “Multi-layer neural networks with local adaptive learning rules for blind separation of source signals”, Proceedings of NOLTA'95, pp. 61–65, NTA Research Society of IE-ICE: Tokyo, Japan, 1995.
E. Weinstein, M. Feder and A. Oppenheim, “Multi-channel signal separation by decorrelation”, IEEE Transactions on Speech and Audio Processing,Vol. 4, No. 1, pp. 405–413, 1993.
D. Yellin and E. Weinstein, “Multichannel signal separation: methods and analysis”, IEEE Transactions on Signal Processing, Vol. 44, No. 1, pp. 106–118, 1996.
K. Torkkola, “Blind separation of convolved sources based on information maximisation”, IEEE Workshop on Neural Networks for Signal Processing, NNSP'96, Seika, Kyoto, Japan, September 4–6, 1996.
A. Bell and T. Sejnowski, “An information maximisation approach to blind separation and blind deconvolution”, Neural Computation, Vol. 7, 1129–1159, 1995.
P. Comon, “Independent component analysis, a new concept?”, Signal Processing, Vol. 36, pp. 87–314, 1994.
J. Karhunen, L. Wang and J. Joutsensalo, “Neural estimation of basis vectors in independent component analysis”, Proc. of the International Conference on Artificial Neural Networks (ICANN ′95), Vol. 1, pp. 317–322, Paris, France, October 9–13, 1995.
M. Girolami and C. Fyfe, “Blind separation of sources using exploratory projection pursuit networks”, in: A. Bulsari (ed) International Conference on the Engineering Applications of Neural Networks, Vol. 1, pp. 249–252, London, 1996.
M. Girolami and C. Fyfe, “Higher order cumulant maximisation using nonlinear Hebbian and anti-Hebbian learning for adaptive blind separation of source signals”, Advances in Computational Intelligence, 3rd International Workshop in Signal and Image Processing, IWSIP'96, Manchester, UK, 4–7 November 1996.
G. Burel, “Blind separation of sources: a nonlinear neural algorithm”, Neural Networks Vol. 5, pp. 937–947, 1992.
K. Matsuoka, O. Masahiro and M. Kawamoto, “A neural net for blind separation of nonstationary signals”, Neural Networks Vol. 8, pp. 411–419, 1995.
J. Herault and C. Jutten, “Space or time adaptive signal processing by neural network models”, AIP Conf. Proc., pp. 206–211, Snowbird, UT, 1986.
H.L. Nguyen Thi and C. Jutten, “Blind source separation for convolutive mixtures”, Signal Processing, Vol. 45, pp. 209–229, 1995.
S. Van Gervan, D. Van Compernolle, H.L. Nguyen Thi and C. Jutten, “Blind separation of sources: a comparative study of 2-nd and a 4-th order solution”, Signal Processing VII: Theories and Applications, pp. 1153–1156, Edinburgh, Scotland, 1994.
P. Foldiak, “Models of sensory coding”, Research Report CUED/F-INFENG/TR91. Physiological Laboratory, University of Cambridge: Cambridge, UK, January 1992.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Girolami, M., Fyfe, C. A temporal model of linear anti-Hebbian learning. Neural Process Lett 4, 139–148 (1996). https://doi.org/10.1007/BF00426022
Issue Date:
DOI: https://doi.org/10.1007/BF00426022