Handwritten digit recognition using multi-layer feedforward neural networks with periodic and monotonic activation functions

Proceedings - International Conference on Pattern Recognition

Volumn 16, Issue 3, 2002, Pages 106-109

  Wong, Kwok Wo ^a   Leung, Chi Sing ^a   Chang, Sheng Jiang ^b  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

^b NANKAI UNIVERSITY   (China)

Author keywords

[No Author keywords available]

Indexed keywords

HANDWITTEN DIGIT RECOGNITION; SIGMOID FUNCTION; SINUSOIDAL FUNCTIONS; ACTIVATION FUNCTIONS; HANDWRITTEN DIGIT RECOGNITION; MULTILAYER FEEDFORWARD NEURAL NETWORKS; NEURONAL ACTIVATION FUNCTION; PERIODIC ACTIVATION FUNCTIONS; PERIODIC FUNCTION;

COMPUTER SIMULATION; FEEDFORWARD NEURAL NETWORKS; LEARNING SYSTEMS; PROBLEM SOLVING; CHEMICAL ACTIVATION; EXTENDED KALMAN FILTERS; NETWORK LAYERS; PATTERN RECOGNITION;

CHARACTER RECOGNITION;

EID: 33751571979     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. Fukushima, K., Miyake, S., and Ito, T.: "Neocognitron: A neural-network model for a mechanism of visual pattern recognition," J.A. Anderson and E. Rosenfeld Eds, Cambridge, MA, MIT press, 1988.
2. Sejnowski, T. J., and Rosenberg, C.R.: "Parallel networks that learn to pronounce English text," Complex Systems, 1987, vol. 1, pp.145-168.
3. Lippmann, R.P.: "Review of neural networks for speech recognition," Neural Computation, 1989, vol. 1, pp.1-38.
4. Dawson, M.R.W, and Schopflocher, D.P., "Modifying the generalized delta rule to train networks of non-monotonic processors for pattern classification," Connection Science, 1992, vol. 4, no. 1, pp. 19-31
5. McCaughan, D.B., "On the properties of Periodic Perceptrons", Proceedings of ICNN, 1997, pp. 188-193.
6. Wong, K.W., and Leung, C.S.: "On-line successive synthesis of wavelet networks", Neural Processing Letters, 1998, vol.7, pp.91-100.
7. Xiaofeng Liao, Kwok-Wo Wong, Chi-Sing Leung, and Zhongfu Wu, "Hopf Bifurcation and Chaos in a Single Delayed Neuron Equation with Nonmonotonic Activation Function," Chaos, Solitons & Fractals, 2001, vol. 12, no. 8, pp. 1535-1547.
8. Singhal, S., and Wu,.L.: "Training feedforward networks with the extended Kalman algorithm," Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1989, pp.1187-1190.
9. Iigunl, Y., Sakai, H., and Tokumaru, H.: "Real-time learning algorithm for a multilayered neural network based on the extended Kalman filter," IEEE Trans. Signal Processing, 1992, vol. 40, pp.959-967.
10. Russell, R.: "Pruning algorithm - a survey", IEEE Trans. Neural Networks, 1993, vol.4, pp.740-747.
11. Yasui, S.: "Convergence suppression and divergence facilitation: minimum and joint use of hidden units by multiple output", Neural Networks, 1997, vol.10, pp.353-367.
12. Leung, C.S, Wong, K.W., Sum, P.P., and Chan, L.W.: "On-line training and pruning for recursive least square algorithms," Electronics Letters, 1996, vol.32, pp. 2152-2153.
13. Wong, A.S.Y., Wong, K.W., and Leung, C.S.: "Recursive least squares approach to combining principal and minor components analyses," Electronics Letters, 1998, vol.34, pp. 1074-1076.
14. Kwok-wo Wong, Chi-sing Leung, and Shengjiang Chang, "The Use of Periodic and Monotonic Activation Functions in Multi-Layer Feedforward Neural Networks Trained by Extended Kalman Filter Algorithm," submitted to IEE Proceedings - Vision. Image and Signal Processing.
15. Shengjiang Chang, Kwok-wo Wong, Chi-sing Leung, "Combining DEKF Algorithm and Trace Rule for Fast On-line Invariance Extraction and Recognition," Pattern Recognition Letters, 2000, Vol. 21, no. 6-7, pp. 493-501.
16. Wallis, G. (1996). Using spatio-temporal correlations to leam invariant object recognition. Neural Networks, 9(9), 1513-1519.
17. LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R.E., Hubbard, W., and Jackel, L.D., Back-propagation applied to handwritten zip code recognition. Neural Computation, 1989, Vol. 1, 541-551.