Growing Neural Gas with Correntropy Induced Metric

This paper discusses the Correntropy Induced Metric (CIM) based Growing Neural Gas (GNG) architecture. CIM is a kernel method based similarity measurement from the information theoretic learning perspective, which quantifies the similarity between probability distributions of input and reference vectors. We apply CIM to find a maximum error region and node insert criterion, instead of euclidean distance based function in original GNG. Furthermore, we introduce the two types of Gaussian kernel bandwidth adaptation methods for CIM. The simulation experiments in terms of the affect of kernel bandwidth σ in CIM, the self-organizing ability, and the quantitative comparison show that proposed model has the superior abilities than original GNG.

[1]  Diego Viejo,et al.  Combining visual features and Growing Neural Gas networks for robotic 3D SLAM , 2014, Inf. Sci..

[2]  David Salomon,et al.  Data Compression: The Complete Reference , 2006 .

[3]  Banchar Arnonkijpanich,et al.  Minimizing the total cost of hen allocation to poultry farms using hybrid Growing Neural Gas approach , 2015, Comput. Electron. Agric..

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  Adil M. Bagirov,et al.  Modified self-organising maps with a new topology and initialisation algorithm , 2015, J. Exp. Theor. Artif. Intell..

[6]  Mustapha Lebbah,et al.  A new Growing Neural Gas for clustering data streams , 2016, Neural Networks.

[7]  Hélio Lopes,et al.  FGNG: A fast multi-dimensional growing neural gas implementation , 2014, Neurocomputing.

[8]  Bernardete Ribeiro,et al.  Clustering and visualization of bankruptcy trajectory using self-organizing map , 2013, Expert Syst. Appl..

[9]  S. Kung.  Kernel Methods and Machine Learning , 2014 .

[10]  Ezequiel López-Rubio,et al.  Learning Topologies with the Growing Neural Forest , 2016, Int. J. Neural Syst..

[11]  Robert Jenssen,et al.  Gaussianization: An Efficient Multivariate Density Estimation Technique for Statistical Signal Processing , 2006, J. VLSI Signal Process..

[12]  Weifeng Liu,et al.  Correntropy: Properties and Applications in Non-Gaussian Signal Processing , 2007, IEEE Transactions on Signal Processing.

[13]  K. S. Venkatesh,et al.  Emotion recognition from geometric facial features using self-organizing map , 2014, Pattern Recognit..

[14]  José García Rodríguez,et al.  3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction , 2016, Neural Processing Letters.

[15]  Babak Mokhtarani,et al.  Prediction of shockwave location in supersonic nozzle separation using self-organizing map classification and artificial neural network modeling , 2016 .

[16]  Luis Eduardo Mujica,et al.  Damage classification in structural health monitoring using principal component analysis and self‐organizing maps , 2013 .

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

[18]  José Carlos Príncipe,et al.  Self-organizing maps with information theoretic learning , 2015, Neurocomputing.

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

[20]  Klaus H. Hinrichs,et al.  Surface-reconstructing growing neural gas: A method for online construction of textured triangle meshes , 2015, Comput. Graph..

[21]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

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