A New Self-Organizing Neural Gas Model based on Bregman Divergences

In this paper, a new self-organizing neural gas model that we call Growing Hierarchical Bregman Neural Gas (GHBNG) has been proposed. Our proposal is based on the Growing Hierarchical Neural Gas (GHNG) in which Bregman divergences are incorporated in order to compute the winning neuron. This model has been applied to anomaly detection in video sequences together with a Faster R-CNN as an object detector module. Experimental results not only confirm the effectiveness of the GHBNG for the detection of anomalous object in video sequences but also its self-organization capabilities.

[1]  Ezequiel López-Rubio,et al.  Bregman Divergences for Growing Hierarchical Self-Organizing Networks , 2014, Int. J. Neural Syst..

[2]  Ezequiel López-Rubio,et al.  Growing Hierarchical Probabilistic Self-Organizing Graphs , 2011, IEEE Transactions on Neural Networks.

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Teuvo Kohonen,et al.  Essentials of the self-organizing map , 2013, Neural Networks.

[5]  Juan Miguel Ortiz-de-Lazcano-Lobato,et al.  Dynamic topology learning with the probabilistic self-organizing graph , 2011, Neurocomputing.

[6]  H. Kushner,et al.  Stochastic Approximation and Recursive Algorithms and Applications , 2003 .

[7]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[8]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[9]  Shin Ishii,et al.  On-line EM Algorithm for the Normalized Gaussian Network , 2000, Neural Computation.

[10]  Xiaogang Wang,et al.  Deep Learning in Object Recognition, Detection, and Segmentation , 2016, Found. Trends Signal Process..

[11]  Andreas Rauber,et al.  The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data , 2002, IEEE Trans. Neural Networks.

[12]  Inderjit S. Dhillon,et al.  Clustering with Bregman Divergences , 2005, J. Mach. Learn. Res..

[13]  Ezequiel López-Rubio,et al.  The Growing Hierarchical Neural Gas Self-Organizing Neural Network , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Thomas Villmann,et al.  Divergence-based classification in learning vector quantization , 2011, Neurocomputing.

[15]  Domingo López-Rodríguez,et al.  Probabilistic PCA Self-Organizing Maps , 2009, IEEE Transactions on Neural Networks.

[16]  L. Bregman.  The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming , 1967 .

[17]  F. Downton.  Stochastic Approximation , 1969, Nature.

[18]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[19]  É. Moulines,et al.  Convergence of a stochastic approximation version of the EM algorithm , 1999 .

[20]  Andrzej Stachurski,et al.  Parallel Optimization: Theory, Algorithms and Applications , 2000, Parallel Distributed Comput. Pract..

[21]  Thomas Villmann,et al.  Divergence-Based Vector Quantization , 2011, Neural Computation.