Input Space Partitioning for Neural Network Learning

To improve the learning performance of neural network NN, this paper introduces an input attribute grouping based NN ensemble method. All of the input attributes are partitioned into exclusive groups according to the degree of inter-attribute promotion or correlation that quantifies the supportive interactions between attributes. After partitioning, multiple NNs are trained by taking each group of attributes as their respective inputs. The final classification result is obtained by integrating the results from each NN. Experimental results on several UCI datasets demonstrate the effectiveness of the proposed method.

[1]  Mikko Lehtokangas Modelling with constructive backpropagation , 1999, Neural Networks.

[2]  Martin R. Varley,et al.  Neuro-Fuzzy Prediction-Based Adaptive Filtering Applied to Severely Distorted Magnetic Field Recordings , 2006, IEEE Geoscience and Remote Sensing Letters.

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

[4]  Gilbert Paquette,et al.  A Multi-Actor Ontology-Based Assistance Model: A Contribution to the Adaptive Semantic Web , 2012 .

[5]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[6]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

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

[8]  Nandish V. Patel Adaptive Evolutionary Information Systems , 2002 .

[9]  Lutz Prechelt,et al.  Investigation of the CasCor Family of Learning Algorithms , 1997, Neural Networks.

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

[11]  S. Sjogaard Generalization in cascade-correlation networks , 1992, Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop.

[12]  Dit-Yan Yeung A Neural Network Approach to Constructive Induction , 1991, ML.

[13]  Thomas G. Dietterich Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[14]  Philip Sedgwick,et al.  Pearson’s correlation coefficient , 2012, BMJ : British Medical Journal.

[15]  Kinshuk,et al.  Intelligent and Adaptive Learning Systems: Technology Enhanced Support for Learners and Teachers , 2011 .

[16]  Timur Ash,et al.  Dynamic node creation in backpropagation networks , 1989 .

[17]  Qi Zhang,et al.  Streamlining Efficient Behaviors for Knowledge Creation in Collaboration , 2013, Int. J. Knowl. Syst. Sci..

[18]  R. Schapire The Strength of Weak Learnability , 1990, Machine Learning.

[19]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

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

[21]  Julie A. McCann,et al.  Support for dynamic trading and runtime adaptability in mobile environments , 2003 .