Interference-less neural network training

The lack of segregation of input space for conventional neural networks (NNs) training often causes interference within the network. The interference-less neural network training (ILNNT) method employed in this paper reduces interference among input attributes by identifying those attributes that interfere with one another and separating them, while attributes that are mutually beneficial are grouped together. Separated attributes in different batches do not share the same hidden neurons while attributes within a batch are connected to the same hidden neurons. ILNNT is applied to widely used benchmark binary and multi-class classification problems and experimental results from K-fold cross validation show that there exist varying degrees of interference among the attributes for the datasets used and the classification accuracy produced by NNs with reduced interference is high.

[1]  Marley M. B. R. Vellasco,et al.  Electric load forecasting: evaluating the novel hierarchical neuro-fuzzy BSP model , 2004 .

[2]  Kwong-Sak Leung,et al.  Medical Data Mining Using Evolutionary Computation , 2022 .

[3]  Andrew K. C. Wong,et al.  A fuzzy approach to partitioning continuous attributes for classification , 2006, IEEE Transactions on Knowledge and Data Engineering.

[4]  Khaled Ahmed Nagaty.  Fingerprints classification using artificial neural networks: a combined structural and statistical approach , 2001, Neural Networks.

[5]  Jun Liu,et al.  An Incremental Approach to Contribution-Based Feature Selection , 2004 .

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

[7]  Demetris Stathakis,et al.  Satellite image classification using granular neural networks , 2006 .

[8]  Ron Sun,et al.  Multi-agent reinforcement learning: weighting and partitioning , 1999, Neural Networks.

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

[10]  L. Su,et al.  Incremental Self-Growing Neural Networks with the Changing Environment , 2001 .

[11]  Yoichi Hayashi,et al.  Combining neural network predictions for medical diagnosis , 2002, Comput. Biol. Medicine.

[12]  Shigeo Abe,et al.  Reducing computations in incremental learning for feedforward neural network with long-term memory , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[13]  Kay Chen Tan,et al.  A Dual-Objective Evolutionary Algorithm for Rules Extraction in Data Mining , 2006, Comput. Optim. Appl..

[14]  Jin Park,et al.  A sequential neural network model for diabetes prediction , 2001, Artif. Intell. Medicine.

[15]  A. Konstantaras,et al.  A neuro-fuzzy approach to the reliable recognition of electric earthquake precursors , 2004 .

[16]  Maysam F. Abbod,et al.  A survey of fuzzy logic monitoring and control utilisation in medicine , 2001, Artif. Intell. Medicine.

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

[18]  Peng Li,et al.  A Hierarchical Incremental Learning Approach to Task Decomposition , 2002 .

[19]  Katsumi Yoshida,et al.  A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders , 2000, Artif. Intell. Medicine.

[20]  Elif Derya Übeyli,et al.  Improving medical diagnostic accuracy of ultrasound Doppler signals by combining neural network models , 2005, Comput. Biol. Medicine.

[21]  Maria Gini,et al.  Partitioning input space for reinforcement learning for control , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[22]  Peng Li,et al.  Feature Selection for Modular Neural Network Classifiers , 2002 .

[23]  Alex Alves Freitas,et al.  A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets , 2004, Artif. Intell. Medicine.

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

[25]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[26]  Tong Heng Lee,et al.  Evolutionary computing for knowledge discovery in medical diagnosis , 2003, Artif. Intell. Medicine.

[27]  Joe Roberts,et al.  Recursively partitioning neural networks for radar target recognition , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[28]  Darius Plikynas,et al.  DECISION RULES EXTRACTION FROM NEURAL NETWORK: A MODIFIED PEDAGOGICAL APPROACH , 2004 .

[29]  Hussein A. Abbass,et al.  An evolutionary artificial neural networks approach for breast cancer diagnosis , 2002, Artif. Intell. Medicine.

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

[31]  Kay Chen Tan,et al.  A Hybrid Multiobjective Evolutionary Algorithm for Solving Vehicle Routing Problem with Time Windows , 2003, Comput. Optim. Appl..

[32]  Mesut Remzi,et al.  Artificial Neural Networks in Urology 2004 , 2004 .

[33]  Marios M. Polycarpou,et al.  Using localizing learning to improve supervised learning algorithms , 2001, IEEE Trans. Neural Networks.

[34]  Lucila Ohno-Machado,et al.  Risk stratification in heart failure using artificial neural networks , 2000, AMIA.