Neural network training for varying output node dimension
Jae-Byung Jung, M.A. El-Sharkawi, Robert J. Marks, Robert T. Miyamoto, Warren L. J. Fox, G.M. Anderson, C.J. Eggen · 2002
Considers the problem of neural network supervised learning when the number of output nodes can vary for differing training data. The paper proposes irregular weight updates and learning rate adjustment to compensate for this variation. In order to compensate for possible over training, an a posteriori probability that shows how often the weights associated with each output neuron are updated is obtained from the training data set and is used to evenly distribute the opportunity for weight update to each output neuron. The weight space becomes smoother and the generalization performance is significantly improved.