International Journal of Computational Intelligence Research (IJCIR)

Volume 2, Number 1 (2006)


Unsupervised Topology Preserving Networks that Learns Sequentially

Palamas George, Papadourakis George
Technological Educational Institute of Crete, Department of Applied Informatics and Multimedia, Greece

Kavoussanos Manolis
Technological Educational Institute of Crete, Department of Mechanical Engineering, Greece

Ware Andrew
University of Glamorgan, school of Computing, United Kingdom


Most of the supervised neural networks for numeral handwriting recognition employ the sigmoidal activation function to generate the outputs. Although this function performs rather well, its computational time as well as its hardware realization is costly and complicated. Here, we introduce a simple activation function in forms of a recursive piecewise polynomial function as an activation function. The accuracy of recognition can be adjusted according to the parameters of the function. In addition a new risk function measuring the discrepancy between the correct and estimated classification of the network is also presented to improve the performance. The proposed activation function and the risk function can achieve the same accuracy compatible with that from the sigmoidal function when tested with the benchmark data set.

Key words
activation function, handwriting recognition, risk function, supervised neural network.