A Pilot Sampling Method for Multi-layer Perceptrons

As the size of samples grows, the accuracy of trained multi-layer perceptrons grows with some improvement in error rates. But we cannot use larger and larger samples, because computational complexity to train the multi-layer perceptrons becomes enormous and data overfitting problem can happen. This paper suggests an effective approach in determining a proper sample size for multi-layer perceptrons with the help of radial basis function networks that work as a pilot for sampling. Experiments with the two neural network algorithms, multi-layer perceptrons and radial basis function networks show very promising results.