论文信息 - TAF neural network for handwritten digits recognition

TAF neural network for handwritten digits recognition

This paper investigates the application of TAF (trainable activation function) neural network to handwritten digit recognition. A three-layer feedforward TAF neural network is used as digits recognizer. Each TAF neuron in the hidden layer acts as a two-class classifier which distinguishes the two pattern classes from each other. The output layer gives output for decision making. While many approaches have bean suggested for this application the proposed method is new and has the advantage of small network size and good recognition performance. Experiments performed on selected digits from NIST database demonstrated that about 99% correct recognition rate has been achieved.

Youshou Wu | Mingsheng Zhao

[1] Xiaoqing Ding,et al. Beyond weights adaptation: a new neuron model with trainable activation function and its supervised learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[2] Teuvo Kohonen,et al. The self-organizing map , 1990 .

[3] Gérard Dreyfus,et al. Handwritten digit recognition by neural networks with single-layer training , 1992, IEEE Trans. Neural Networks.

[4] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[5] James A. Pittman,et al. Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning , 1991, Neural Computation.

[6] Bernard Lemarié,et al. Practical Realization of a Radial Basis Function Network for Handwritten Digit Recognition , 1993, IWANN.

[7] Bernard Lemarie,et al. Radial Basis Function network for handwritten digit recognition , 1993, Defense, Security, and Sensing.

[8] H. Lim,et al. Combining Neural Network and Stroke-Based Method for Handwritten Numeral Recognition and its Application to Tax-form Processing , 1997, ICONIP.