Abstract
In this paper, the problem that we are interested is constructing \(l_{1}\)-graphs for subspace learning via recurrent neural networks. We propose a closed affine subspace learning (CASL) method to do so. The problem of CASL is formulated as an optimization problem described by an energy function in the non-negative orthant. The sufficient conditions for keeping the minimum points of the energy function in the non-negative orthant are given. A model of Lotka–Volterra recurrent neural networks is constructed to solve the optimization problem in terms of these sufficient conditions. It shows that the set of stable attractors of the network model just equals the set of minimum points of the energy function in the non-negative orthant. Based on these equivalences, the problem of CASL can be solved by running the proposed LV RNNs to obtain the stable attractors. The \(l_{1}\)-graphs then can be constructed. Experiments on some synthetic and real data show that the \(l_{1}\)-graphs constructed in this way are more effective, especially when processing the data sampled from multiple manifolds.
Similar content being viewed by others
References
Asai T, Ohtani M, Yonezu H (1999) Analog integrated circuits for the lotka-volterra competitive neural networks. IEEE Trans Neural Netw 10(5):1222–1231
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
Belkin M, Matveeva I, Niyogi P (2004) Regularization and semi-supervised learning on large graphs. In: Learning theory. Springer, Berlin, pp 624–638
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434
Brox T, Malik J (2010) Object segmentation by long term analysis of point trajectories. In: Computer vision-ECCV 2010. Springer, Berlin, pp 282–295
Chen G, Lerman G (2009) Spectral curvature clustering (scc). Int J Comput Vis 81(3):317–330
Cheng B, Yang J, Yan S, Fu Y, Huang TS (2010) Learning with l 1-graph for image analysis. IEEE Trans Image Process 19(4):858–866
Donoho DL, Grimes C (2003) Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc Natl Acad Sci 100(10):5591–5596
Elhamifar E, Vidal R (2009) Sparse subspace clustering. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE, pp 2790–2797
Elhamifar E, Vidal R (2011) Sparse manifold clustering and embedding. In: Advances in neural information processing systems, pp 55–63
Fukai T, Tanaka S (1997) A simple neural network exhibiting selective activation of neuronal ensembles: from winner-take-all to winners-share-all. Neural Comput 9(1):77–97
Ge SS, Guan F, Loh A, Fua CH (2006) Feature representation based on intrinsic structure discovery in high dimensional space. In: Robotics and Automation, 2006. ICRA 2006. IEEE Conference on Proceedings 2006. IEEE, pp 3399–3404
Grant M, Boyd S, Ye Y (2008) Cvx: Matlab software for disciplined convex programming
Guan N, Tao D, Luo Z, Yuan B (2011a) Manifold regularized discriminative nonnegative matrix factorization with fast gradient descent. IEEE Trans Image Process 20(7):2030–2048
Guan N, Tao D, Luo Z, Yuan B (2011b) Non-negative patch alignment framework. IEEE Trans Neural Netw 22(8):1218–1230
Guan N, Tao D, Luo Z, Shawe-Taylor J (2012a) Mahnmf: Manhattan non-negative matrix factorization. arXiv, preprint arXiv:12073438
Guan N, Tao D, Luo Z, Yuan B (2012b) Nenmf: an optimal gradient method for nonnegative matrix factorization. IEEE Trans Signal Process 60(6):2882–2898
Lauer F, Schnorr C (2009) Spectral clustering of linear subspaces for motion segmentation. In: IEEE transactions on computer vision. IEEE, pp 678–685
Lei YK, Xu YM, Yang JA, Ding ZG, Gui J (2012) Feature extraction using orthogonal discriminant local tangent space alignment. Pattern Anal Appl 15(3):249–259
Liu G, Yan S (2011) Latent low-rank representation for subspace segmentation and feature extraction. In: 2011 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 1615–1622
Ng AY, Jordan MI, Weiss Y et al (2002) On spectral clustering: analysis and an algorithm. Adv Neural Inf Process Syst 2:849–856
Nistér D (2005) Preemptive ransac for live structure and motion estimation. Mach Vis Appl 16(5):321–329
Pan Y, Ge SS (2009) Weighted locally linear embedding for dimension reduction. Pattern Recognit 42(5):798–811
Rao SR, Tron R, Vidal R, Ma Y (2008) Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories. In: IEEE conference on computer vision and pattern recognition, 2008. CVPR 2008. IEEE, pp 1–8
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Saul LK, Roweis ST (2003) Think globally, fit locally: unsupervised learning of low dimensional manifolds. J Mach Learn Res 4:119–155
Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888–905
Short R, Fukunaga K (1980) A new nearest neighbor distance measure. In: Proceedings of the fifth international Conference on Pattern Recognition, pp 81–86
Tenenbaum JB (1998) Mapping a manifold of perceptual observations. In: Advances in neural information processing systems, pp 682–688
Tomasi C, Kanade T (1992) Shape and motion from image streams under orthography: a factorization method. Int J Comput Vis 9(2):137–154
Tron R, Vidal R (2007) A benchmark for the comparison of 3-d motion segmentation algorithms. In: IEEE conference on computer vision and pattern recognition, 2007. CVPR’07. IEEE, pp 1–8
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognit Neurosci 3(1):71–86
Van Den Berg E, Friedlander MP (2008) Probing the pareto frontier for basis pursuit solutions. SIAM J Sci Comput 31(2):890–912
Vidal R, Hartley R (2004) Motion segmentation with missing data using powerfactorization and gpca. In: Computer Vision and Pattern Recognition, 2004. CVPR 2004. In: IEEE computer society conference on proceedings of the 2004. IEEE, vol 2, pp II-310
Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Xu D, Yan S, Tao D, Lin S, Zhang HJ (2007) Marginal fisher analysis and its variants for human gait recognition and content-based image retrieval. IEEE Trans Image Process 16(11):2811–2821
Yan J, Pollefeys M (2006) A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In: Computer vision-ECCV 2006. Springer, Berlin, pp 94–106
Yan S, Xu D, Zhang B, Zhang HJ, Yang Q, Lin S (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29(1):40–51
Yang B, Chen S, Wu X (2011) A structurally motivated framework for discriminant analysis. Pattern Anal Appl 14(4):349–367
Yi Z (2010) Foundations of implementing the competitive layer model by lotka-volterra recurrent neural networks. IEEE Trans Neural Netw 21(3):494–507
Yi Z, Tan K (2002) Dynamic stability conditions for lotka-volterra recurrent neural networks with delays. Phys Rev E 66(1):011910
Yu J, Amores J, Sebe N, Radeva P, Tian Q (2008) Distance learning for similarity estimation. IEEE Trans Pattern Anal Mach Intell 30(3):451–462
Zhang Y, Tan KK (2003) Convergence analysis of recurrent neural networks. Kluwer academic, Boston
Zhu X, Ghahramani Z, Lafferty J et al (2003) Semi-supervised learning using gaussian fields and harmonic functions. ICML 3:912–919
Acknowledgments
This work was supported by National Basic Research Program of China (973 Program) under Grant No. 2011CB302201, Program for New Century Excellent Talents in University under Grant No. NCET-11-0355, and Doctoral Fund of Ministry of Education of China under Grants Nos. 20100181120030 and 20110181110049.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kuang, Y., Zhang, L. & Yi, Z. Constructing \(L_{1}\)-graphs for subspace learning via recurrent neural networks. Pattern Anal Applic 18, 817–828 (2015). https://doi.org/10.1007/s10044-014-0370-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-014-0370-1