Abstract
This paper presents a highly scalable modular bottleneck neural network and its application to image dimensionality reduction and image transformation. The network is a three-dimensional lattice of modules that implements a complex mapping with full connectivity between two high-dimensional datasets. These datasets correspond to input and output pixel-based images of three airplanes with various spatial orientations. The modules are multilayer perceptrons trained with Levenberg-Marquardt method on GPUs. They are locally connected together in an original manner that allows the gradual elaboration of the global mapping. The lattice of modules is squeezed in its middle into a bottleneck, thereby reducing the dimensionality of images. Afterward, the bottleneck itself is stretched to enforce a specific transformation directly on the reduced data. Analysis of the neural values at the bottleneck shows that we can extract from them robust and discriminative descriptors of the airplanes. The approach compares favorably to other dimensionality reduction techniques.
Similar content being viewed by others
References
Carcenac M (2008) A modular neural network applied to image transformation and mental images. Neural Comput Appl 17(5):549–568
Osherson DN, Weinstein S, Stoli M (1990) Modular learning. In: Schwartz EL (ed) Computational neuroscience. MIT Press, Cambridge, MA, pp 369–377
Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixtures of local experts. Neural Comput 3:79–87
Jordan MI (1994) A statistical approach to decision tree modeling. Proceedings of the ACM Conference on Computer Learning Theory
Wu CL, Chau KW, Fan C (2010) Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. J Hydrol 389(1-2):146–167
Carcenac M (2009) A modular neural network for super-resolution of human faces. Appl Intell 30(2):168–186
Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. AIChE J 37(2):233–243
CUDA Toolkit Documentation http://docs.nvidia.com/cuda, Nvidia Corporation
Linsker R (1986) From basic network principles to neural architecture: emergence of spatial-opponent cells. P Natl Acad Sci USA 83:7508–7512
Linsker R (1988) Self-organization in a perceptual network. Computer 21(3):105–117
LeCun Y (1993) Efficient learning and second-order methods. A tutorial at NIPS 93, Denver
Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Soc Ind Appl Math 11(2):431–441
Hinton GE (1989) Connectionist learning procedures. Artif Intell 40:185–234
Hsieh WW, Tang B (1998) Applying neural network models to prediction and data analysis in meteorology and oceanography. B Am Meteorol Soc 79(9):1855–1870
CUDA Toolkit Documentation http://docs.nvidia.com/cuda/cublas, Nvidia Corporation
Carcenac M (2014) From tile algorithm to stripe algorithm: a CUBLAS-based parallel implementation on GPUs of Gauss method for the resolution of extremely large dense linear systems stored on an array of solid state devices. J Supercomput 68(1):365–413
Buttari A, Langou J, Kurzak J, Dongarra J (2009) A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput 35:38–53
Agullo E, Augonnet C, Dongarra J, Faverge M, Langou J, Ltaief H, Tomov S (2011) LU factorization for accelerator-based systems AICCSA’ 11 Conference 217–224
Hsieh WW (2001) Nonlinear principal component analysis by neural networks. Tellus 53A:599–615
Monahan AH (2001) Nonlinear principal component analysis: tropical Indo-Pacific sea surface temperature and sea level pressure. J Climate 14:219–233
Hsieh WW (2007) Nonlinear principal component analysis of noisy data. Neural Netw 20:434–443
3D models http://www.turbosquid.com, TurboSquid
Monahan AD (2000) Nonlinear principal component analysis by neural networks: theory and application to the Lorentz system. J Climate 13:821–835
Lorenz EN (1963) Deterministic nonperiodic flow. J Atmos Sci 20:130–141
Kirby MJ, Miranda R (1996) Circular nodes in neural networks. Neural Comput 8:390–402
Bengio Y, LeCun Y (2007) Scaling learning algorithms towards AI. In: Bottou L, Chapelle O, DeCoste D, Weston J (eds) Large Scale Kernel Machines. MIT, Press, Cambridge, MA, pp 321–360
Chen K (2015) Deep and Modular Neural Networks Kacprzyk J, Pedrycz W (eds)
Bengio Y (2009) Learning Deep Architectures for AI. Found and Trends in Mach Learn 2(1):1–127
Hinton GE, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(9):1527–1554
Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning J Mach Learn Res 11:625–660
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS-10), 249–256
Schmidhuber J (2014) Deep Learning in Neural Networks: An Overview. Technical Report IDSIA-03-14. arXiv:1404.7828v4
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504– 507
Salakhutdinov RR, Hinton GE Training a deep autoencoder or a classifier on MNIST digits. http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html
Kailath T (1980) Linear systems. Prentice-Hall, Englewood Cliffs, NJ
McWhirter JG, Baxter PD, Cooper T, Redif S, Foster J (2007) An EVD algorithm for para-Hermitian polynomial matrices. IEEE T Signal Proces 55(5):2158–2169
Redif S, McWhirter JG, Weiss S (2011) Design of FIR paraunitary filter banks for subband coding using a polynomial eigenvalue decomposition. IEEE T Signal Proces 59(11):5253–5264
Redif S, McWhirter JG, Baxter P, Cooper T (2006) Robust broadband adaptive beamforming via polynomial eigenvalues Proceedings of the IEEE Oceans Conference, 1–6
Weiss S, Redif S, Cooper T, Liu C, Baxter PD, McWhirter JG (2006) Paraunitary oversampled filter bank design for channel coding. EURASIP J Appl Si Pr 2006:1–10
Ta CH, Weiss S (2007) A design of precoding and equalisation for broadband MIMO systems. Proceedings of the 15th International Conference on Digital Signal Processing, Cardiff, UK, 571–574
Alrmah MA, Weiss S, Redif S, Lambotharan S, McWhirter JG (2013) Angle of arrival estimation for broadband signals: A comparison. Proceedings of the Intelligent Signal Processing Conference, IET, London, UK
Redif S, Weiss S, McWhirter JG (2015) Sequential matrix diagonalisation algorithms for polynomial EVD of parahermitian matrices. IEEE T Signal Proces 63(1):81–89
Corr J, Thomson K, Weiss S, McWhirter JG, Redif S, Proudler IK (2014) Multiple shift maximum element sequential matrix diagonalisation for parahermitian matrices. Proceedings of the IEEE Workshop on Statistical Signal Processing, Gold Coast, Australia, 312–315
Krauth W, Mézard M, Nadal JP (1988) Basins of attraction in a perceptron-like neural network. Complex Syst 2:387–408
Uppala SM, Kallberg PW, Simmons AJ, Andrae U, Da Costa Bechtold V, Fiorino M, Gibson JK, Haseler J, Hernandez A, Kelly GA, Li X, Onogi K, Saarinen S, Sokka N, Allan RP, Andersson E, Arpe K, Balmaseda MA, Beljaars ACM, Van De Berg L, Bidlot J, Bormann N, Caires S, Chevallier F, Dethof A, Dragosavac M, Fisher M, Fuentes M, Hagemann S, Holm E, Hoskins BJ, Isaksen L, Janssen PAEM, Jenne R, Mcnally AP, Mahfouf JF, Morcrette JJ, Rayner NA, Saunders RW, Simon P, Sterl A, Trenberth KE, Untch A, Vasiljevic D, Viterbo P, Woollen J (2005) The ERA-40 re-analysis. Q J Roy Meteor Soc 131(612):2961–3012
Acknowledgments
The authors are thankful to Nvidia Corporation for their donation of the C2075 and the GTX480 GPUs used for the experiments reported in this paper. We wish to thank the reviewers of this paper for their insightful comments and suggestions. We also thank Prof. Ian K. Proudler, of Loughborough University, UK, and Prof. Isaac Lerner for reviewing the manuscript and for offering suggestions toward its improvement.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Carcenac, M., Redif, S. A highly scalable modular bottleneck neural network for image dimensionality reduction and image transformation. Appl Intell 44, 557–610 (2016). https://doi.org/10.1007/s10489-015-0715-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-015-0715-5