Generalization in ANN—Some Empirical Results for Handwritten Numeral Recognition
Sachin Ratikant Gengaje, A. R. Yardi · IETE Journal of Research · 2000
In this paper, some input schemes, output representation schemes and learning factors are examined to improve generalization in feedforward three layer Artificial Neural Network with application to handwritten numeral recognition.The paper focuses on simple experiments with the raw input i.e. no features are extracted. Input schemes discussed includes training with normal training set and extended training set. Output representations include normal 4 bit and 10 bit coding. Experiments are conducted with different learning rates and techniques of ‘weight smoothing’ is used. Lastly it is observed that the network size can be curtailed by removing some of the input neurons which are not contributing much with very little effect on generalization ability of the network.