A Dual Network Adaptive Learning Algorithm for Supervised Neural Network with Contour Preserving Classification for Soft Real Time Applications

A framework presenting a basic conceptual structure used to solve adaptive learning problems in soft real time applications is proposed Its design consists of two supervised neural networks running simultaneously One is used for training data and the other is used for testing data The accuracy of the classification is improved from the previous works by adding outpost vectors generated from prior samples The testing function is able to test data continuously without being interrupted while the training function is being executed The framework is designed for a parallel processing and/or a distributed processing environment due to the highly demanded processing power of the repetitive training process of the neural network.

[1]  Jude W. Shavlik,et al.  Using Sampling and Queries to Extract Rules from Trained Neural Networks , 1994, ICML.

[2]  Helmut Mayer.  Rule Extraction from Artificial Neural Networks , 2006 .

[3]  Piyabute Fuangkhon,et al.  An incremental learning algorithm for supervised neural network with contour preserving classification , 2009, 2009 6th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[4]  Udo Seiffert,et al.  Artificial Neural Networks on Massively Parallel Computer Hardware , 2004, ESANN.

[5]  David Calvert,et al.  Distributed artificial neural network architectures , 2005, 19th International Symposium on High Performance Computing Systems and Applications (HPCS'05).

[6]  Thitipong Tanprasert,et al.  An approach to control aging rate of neural networks under adaptation to gradually changing context , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[7]  Bernd Fritzke.  Incremental Learning of Local Linear Mappings , 1995 .

[8]  V. Burzevski,et al.  Hierarchical growing cell structures , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[9]  Vasant Honavar,et al.  Learn++: an incremental learning algorithm for supervised neural networks , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[10]  Yadong Wang,et al.  Research and Design of Distributed Neural Networks with Chip Training Algorithm , 2005, ICNC.

[11]  Rudy Setiono,et al.  Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting , 1997, Neural Computation.

[12]  B. Fritzke,et al.  A growing and splitting elastic network for vector quantization , 1993, Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop.

[13]  Tom Michael Mitchell.  Learning Analytically and Inductively , 1995 .

[14]  Bernd Fritzke.  Vector Quantization with a Growing and Splitting Elastic Net , 1993 .

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

[16]  Chidchanok Lursinsap,et al.  Contour preserving classification for maximal reliability , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[17]  Piyabute Fuangkhon,et al.  An Adaptive Learning Algorithm for Supervised Neural Network with Contour Preserving Classification , 2009, AICI.

[18]  Sebastian Thrun,et al.  Integrating Inductive Neural Network Learning and Explanation-Based Learning , 1993, IJCAI.

[19]  Bo Yang,et al.  Research and design of distributed training algorithm for neural networks , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[20]  Giovanni Soda,et al.  Unified Integration of Explicit Knowledge and Learning by Example in Recurrent Networks , 1995, IEEE Trans. Knowl. Data Eng..

[21]  Jude W. Shavlik,et al.  Knowledge-Based Artificial Neural Networks , 1994, Artif. Intell..

[22]  Ron Sun,et al.  Beyond Simple Rule Extraction: Acquiring Planning Knowledge from Neural Networks , 2001, WIRN.