Linear Feature Sensibility for Output Partitioning in Ordered Neural Incremental Attribute Learning

Feature Ordering is a special training preprocessing for Incremental Attribute Learning IAL, where features are trained one after another. Since most feature ordering calculation methods, compute feature ordering in one batch, no matter, this study presents a novel approach combining input feature ordered training and output partitioning for IAL to compute feature ordering with considering whether the output of the classification problem is univariate or multivariate. New metric called feature's Single Sensibility SS is proposed to individually calculate features' discrimination ability for each output. Finally, experimental benchmark results based on neural networks in IAL show that SS is applicable to calculates feature's discrimination ability. Furthermore, combined output partitioning can also improve further the final classification performance effectively.

[1]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Steven Guan,et al.  Incremental Learning with Respect to New Incoming Input Attributes , 2004, Neural Processing Letters.

[3]  Steven Guan,et al.  Incremental attribute based particle swarm optimization , 2012, 2012 8th International Conference on Natural Computation.

[4]  Peng Li,et al.  Incremental Learning in Terms of Output Attributes , 2004 .

[5]  Fangming Zhu,et al.  A new approach to mining fuzzy databases using nearest neighbor classification by exploiting attribute hierarchies , 2004 .

[6]  En Zhu,et al.  An Incremental Feature Learning Algorithm Based on Least Square Support Vector Machine , 2008, FAW.

[7]  Ting Wang,et al.  Optimized Neural Incremental Attribute Learning for Classification Based on Statistical discriminability , 2014, Int. J. Comput. Intell. Appl..

[8]  Kai Wang,et al.  Hierarchical Incremental Class Learning with Output Parallelism , 2007 .

[9]  Ting Wang,et al.  Evolving Linear Discriminant in a Continuously Growing Dimensional Space for Incremental Attribute Learning , 2012, NPC.

[10]  Ting Wang,et al.  Feature Ordering for Neural Incremental Attribute Learning Based on Fisher's Linear Discriminant , 2013, 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics.

[11]  Fai Wong,et al.  An incremental decision tree learning methodology regarding attributes in medical data mining , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[12]  Ting Wang,et al.  Pattern classification with ordered features using mRMR and neural networks , 2010, 2010 International Conference on Information, Networking and Automation (ICINA).

[13]  Abdullah Al Mamun,et al.  Interference-less neural network training , 2008, Neurocomputing.

[14]  Jun Liu,et al.  Incremental Ordered Neural Network Training , 2002 .

[15]  Steven Guan,et al.  An incremental approach to genetic-algorithms-based classification , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Fei Liu,et al.  Feature Discriminability for Pattern Classification Based on Neural Incremental Attribute Learning , 2011 .

[17]  Ting Wang,et al.  Entropic Feature Discrimination Ability for Pattern Classification Based on Neural IAL , 2012, ISNN.

[18]  Ting Wang,et al.  Correlation-based Feature Ordering for Classification based on Neural Incremental Attribute Learning , 2012 .

[19]  Jun Liu,et al.  Incremental Neural Network Training with an Increasing Input Dimension , 2004 .

[20]  Steven Guan,et al.  Parallel growing and training of neural networks using output parallelism , 2002, IEEE Trans. Neural Networks.