Fuzzy Neuro Systems for Machine Learning for Large Data Sets

1
Fuzzy Neuro Systems for Machine Learning for
Large Data Sets

• Rahul Kala,
• Department of Information Technology
• Indian Institute of Information Technology and
  Management Gwalior
• http//students.iiitm.ac.in/ipg_200545/
• rahulkalaiiitm_at_yahoo.co.in, rkala_at_students.iiitm.a
  c.in

Paper Kala, Rahul Shukla, Anupam Tiwari, Ritu,
Fuzzy Neuro Systems for Machine Learning for
Large Data Sets, Proceedings of the IEEE
International Advance Computing Conference,
ieeexplore, pp 541-545, Digital Object Identifier
10.1109/IADCC.2009.4809069, 6-7 March 2009,
Patiala, India
2
Data Size

• In General,
• More the training data, better the performance

• Large training sets
• High dimensionality
• High classification classes

3
Problems in Neural Networks
4
The Basic Idea
5
The Algorithm
6
The Hierarchical Nature

7
The Approach in Input Space
8
Results
9
Fuzzy C Means Clustering
10
Results
11
Conclusion

• Training Time
• Training Efficiency

12
References

• Alves, R.Lde.S. de Melo, J.D. Neto, A.D.D. and
  Albuquerque, A.C.M.L, New parallel algorithms
  for back-propagation learning, Proceedings of
  the 2002 International Joint Conference on Neural
  Networks, 2002. IJCNN '02, pp 2686-2691, 2002
• Amin, Md. Faijul Murase, K., Single-layered
  complex-valued neural network for real-valued
  classification problems, Neurocomputing (2008),
  doi10.1016/j.neucom.2008.04.006
• Ang, J.H. et al., Training neural networks for
  classification using growth probability-based
  evolution, Neurocomputing (2008),
  doi10.1016/j.neucom.2007.10.011
• Azari, N.G. and Lee, S.-Y, Hybrid partitioning
  for particle-in-cell simulation on shared memory
  systems, Proc. of 11th International Conference
  on Distributed Computing Systems, 20-24 May 1991,
  pp. 526-533.
• Babii, Sorin Cretu, Vladimir Petriu, Emil M.,
  Performance Evaluation of Two Distributed
  BackPropagation Implementations, Proceedings of
  International Joint Conference on Neural
  Networks, Orlando, Florida, USA, August 12-17,
  2007
• Campobello, Giuseppe Patane, Giuseppe and Russo,
  Marco, An efficient algorithm for parallel
  distributed unsupervised learning,
  Neurocomputing, Volume 71, Issues 13-15, August
  2008, Pages 2914-2928
• Draghici Sorin, A neural network based
  artificial vision system for licence plate
  recognition?, international Journal of Network
  Security, International Journal of Neural
  Systems, Vol. 8, No. 1, 1997
• Er, Meng Joo Zhou, Yi, A novel framework for
  automatic generation of fuzzy neural networks,
  Neurocomputing, 71 (2008) 584591
• 9 Estevez, Pablo A Paugam-Moisy, Helene,
  Puzenat , Didier , Ugarte, Manuel, A scalable
  parallel algorithm for training a hierarchical
  mixture of neural experts, Parallel Computing 28
  (2002) 861891
• Feng, Zhonghui Zhou, Bing and Shen, Junyi, A
  parallel hierarchical clustering algorithm for
  PCs cluster system, Neurocomputing Volume 70,
  Issues 4-6, January 2007, Pages 809-818
• Graves Alex, Fernandez Santiago, Liwicki Marcus,
  Bunke Horst, Schmidhuber Jurgen, Unconstrained
  Online Handwriting Recognition with Recurrent
  Neural Networks?, Advances in Neural Information
  Processing Systems 20, 2008
• Hanzalek Zdenek, A Parallel algorithm for
  gradient training of feedforward neural
  networks, Pattern Computing, 24(1998), 823-839

13

• Jia, Zhen, Balasuriya, Arjuna and Challa,
  Subhash, Sensor fusion-based visual target
  tracking for autonomous vehicles with the
  out-of-sequence measurements solution, Robotics
  and Autonomous Systems Volume 56, Issue 2, 29
  February 2008, Pages 157-176
• Kak, S.C. New algorithms for training
  feedforward neural networks, Pattern Recognition
  Letters, 15, 295-298 (1994).
• Kak, Subhash C., On generalization by neural
  networks, ELSEVIER Information Sciences 111
  (1998) 293-302
• Lin, Cheng-Jian Hong, Shang-Jin, The design of
  neuro-fuzzy networks using particle swarm
  optimization and recursive singular value
  decomposition, Neurocomputing 71 (2007) 297310
• Madineni, K.B., Two corner classication
  algorithms for training the Kak feedforward
  neural network. Information Sciences 81, 229-234
  (1994).
• Mohanty, S. Bhattacharya, S Recognition of
  Voice signals for Oriya Language using wavelet
  Neural Network, ACM International Journal of
  Expert Systems with Applications, Vol 34, Issue
  3, pp 2130-2147, April 2008
• Ozdzynski, Piotr Lin, Andy Liljeholm, Mimi and
  Beatty, Jackson, A parallel general
  implementation of Kohonen's self-organizing map
  algorithm performance and scalability,
  Neurocomputing Volumes 44-46, June 2002, Pages
  567-571
• Pagac, D., Nebot, E. M. and Durrant. W., H., An
  evidential approach to map building for
  autonomous robots, IEEE Trans. On Robotics and
  Automation, vol.14, no.2, pp. 623-629, Aug. 1998.
• Papakostas, G. A., Karras D. A., Mertzios B. G.,
  and Boutalis, Y. S, An Efficient Feature
  Extraction Methodology for Computer Vision
  Applications using Wavelet Compressed Zernike
  Moments, ACM International Journal of
  Information Sciences, Vol 177, Issue 13, 2007
• Purwin, Oliver DAndrea, Raffaello Lee,
  Jin-Woo Theory and implementation of path
  planning by negotiation for decentralized agents
  , Robotics and Autonomous Systems Volume 56,
  Issue 5, 31 May 2008, Pages 422-436
• Sandhu , Parvinder Singh Salaria, Dalwinder
  Singh Singh , Hardeep, A Comparative Analysis
  of Fuzzy, Neuro-Fuzzy and Fuzzy-GA Based
  Approaches for Software Reusability Evaluation,
  Proceedings of Worls Academy of Science,
  Engineering and Technology Volume 29 May, 2008,
  ISSN 1307-6884
• Shukla, Anupam Tiwari, Ritu, Fusion of Face and
  Speech Features with Artificial Neural Network
  for Speaker Authentication, IETE Technical
  Review, Vol 24, No 5, September-October 2007, pp
  359-368
• Suresh, S. Omkar, S.N. and Mani, V, Parallel
  Implementation of Back-Propagation Algorithm in
  Networks of Workstations, IEEE Transactions on
  Parallel and Distributed Systems, Vol 16, No 1,
  pp 24-34, January, 2005
• Taur, J.S. Tao, C.W., A New Neuro-Fuzzy
  Classifier with Application to On-Line Face
  Detection and Recognition, Journal of VLSI
  Signal Processing 26, 397409, 2000
• Vieira, Armando Barradas, Nuno A training
  algorithm for classification of high-dimensional
  data, Neurocomputing 50 (2003) 461 472