Learning Flexible Neural Networks for Pattern Recognition

Authors: A. Mirzaaghazadeh, H. Motameni, M. Karshenas, H. Nematzadeh

Abstract:

Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.

Keywords: Back propagation, Flexible, Gradient, Learning, Neural network, Pattern recognition.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1086271

References:

[1] A. Mirzaaghazadeh, H. Motameni, "Using Neural Network in Pattern Recognition", Proceeding of Iran Computer Conference, 2002.
[2] Kamarthi S.V., Pittner S. , Accelerating neural network traning using weight extrapolation, Neural networks, 9, 1999, pp. 1285-1299.
[3] A. Burak Goktepe, "Role of Learning Algorithm in Neural Network- Based Back calculation of Flexible Pavements", Journal of Computing in Civil Engineering, Volume 20, Issue 5, pp. 370-373 (September/October 2006).
[4] Manfred M Fisher, "Neural Networks: A General Framework for Non- Linear Function Approximation", Transactions in GIS, Volume 10 Page 521 - july 2006, doi:10.1111/j.1467-9671.2006.01010.x, Volume 10 Issue 4.
[5] V. Maiorov, "Approximation by neural networks and learning theory", Journal of Complexity, Volume 22, Issue 1, Februery 2006, Pages 102- 117.
[6] Salvatore Cavalieri, "A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks", Neural Networks, Volume 12, Issue 1, January 1999, Pages 91-106.
[7] Mohammad Teshnehlab and Keigo Watanabe (Eds.), "Intelligent control based on flexible neural networks", Kluwer Academic Publishers, Dordrecht, The Netherlands, 1999, ISBN 0-7923 -5683-7, Automatica, Volume 38, Issue 3, March 2002, Pages 564-565.
[8] Edgar Rinast, HansDieter Weiss, "Neural network approach computer=assisted interpretation of ultrasound images of the gallbladder", Europen Journal of Radiology, Volume 17, Issue 3, November 1993, Pages 175-178.
[9] K. Economou and D. Lymberopoulos, "A new perspective in learning pattern generation for teaching neural networks", Neural Networks, Volume 12, Issue 4-5, June 1999, Pages 767-775.
[10] Eiji Mizutani and James W. Demmel, "On structure-exploiting trustregion regularized nonlinear least squares algorithms for neural-network learning", Neural Networks, Volume 16, Issue 5-6, June-July 2003, pages 745-753.
[11] R.Vicente Ruiz de angulo and Carme Torras, "Neural learning methods yielding functional invaiance", Theoretical Computer Science, Volume 320, Issue 1, 12 June 2004, Pages 111-121.
[12] Solanki Gautam, "Neural network and its application in pattern recognition", Seminar Report of Department of Computer Science and Engg. Indian Institue of Technology, Bombay, November 5, 2004.
[13] Alexander J. Faaborg, "Using neural networks to create an adaptive character recognition system", March 2002, http://web.media.mit.edu/~faaborg/research/cornell/hci_neuralnetwork_f inalpaper.pdf
[14] O. Lezray, D. Fournier and H. Cardot, "Neural network induction graph for pattern recognition", Neurocomputing 57 (2004) 257-274.