A fast algorithm for the hidden units in a multilayer perceptron
Minoru Hayashi · 2005
We propose an online algorithm for deciding the smallest possible number of neurons in a hidden layer of the backpropagation model for the best possible operation based on singular value decomposition. Our simulations showed that the algorithm proposed works very well for character recognition. We conclude that the algorithm can be a powerful tool for solving a general classification problem with an optimized neural network.