A perception evolution network for unsupervised fast incremental learning

A perception evolution network (PEN) is proposed for unsupervised fast incremental (or on-line) learning in this paper. The network has two layers: the perception layer receives the external data from the reality environment and the knowledge layer learns and records the knowledge contained in the data from the perception layer in incremental and self-organizing way. In PEN model, new input channels can be added to the perception layer freely during learning. When the perception layer gets some new input channels, the network will create corresponding data transmission channels to the knowledge layer. The prior learned knowledge stored in the knowledge layer will be expanded to a higher-dimensional space which contains the attributes of the new input channels. For incremental (or on-line) learning, PEN can automatically obtain suitable prototypes and find the topology structure of the learning data without any priori knowledge. The noise processing mechanism guarantees PEN can work in the complex real-world (noisy) environment. The experiments for both artificial data set and real-world data set show that the proposed method is effective.

[1]  Shen Furao,et al.  An online incremental learning pattern-based reasoning system , 2010, Neural Networks.

[2]  Marcos Faúndez-Zanuy,et al.  Biometric recognition using online uppercase handwritten text , 2012, Pattern Recognit..

[3]  Shen Furao,et al.  An enhanced self-organizing incremental neural network for online unsupervised learning , 2007, Neural Networks.

[4]  Stephen Grossberg,et al.  The ART of Adaptive Pattern Recognition Self-organizing by a Neu Network , 1988 .

[5]  Marko Tscherepanow,et al.  A hierarchical ART network for the stable incremental learning of topological structures and associations from noisy data , 2011, Neural Networks.

[6]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[7]  Mubarak Shah,et al.  Learning semantic features for action recognition via diffusion maps , 2012, Comput. Vis. Image Underst..

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

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

[10]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[11]  Shen Furao,et al.  An incremental network for on-line unsupervised classification and topology learning , 2006, Neural Networks.

[12]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[13]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[14]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[15]  A. Martínez,et al.  The AR face databasae , 1998 .

[16]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.