An analysis of premature saturation in back propagation learning

Baba, 1989, A new approach for finding the global minimum of error function of neural networks, Neural Networks, 2, 367, 10.1016/0893-6080(89)90021-X Baba, 1990, A hybrid algorithm for finding global minimum of error function of neural networks, I, 585 Chen, 1990, Stepsize variation for accelerating the back propagation algorithm, I, 601 Cheung, 1990, Relative effectiveness of training set patterns for back propagation, I, 673 Hecht-Nielsen, 1989, Theory of backpropagation neural networks, I, 593 Hecht-Nielsen, 1989, HNC Neurosoftware Documents, 2 Hornik, 1989, Multilayer feedforward networks are universal approximators, Neural Networks, 2, 359, 10.1016/0893-6080(89)90020-8 Jacobs, 1988, Increased rates of convergence through learning rate adaptation, Neural Networks, I, 295, 10.1016/0893-6080(88)90003-2 Kollias, 1989, An adaptive least squares algorithm for the efficient training of artificial neural networks, IEEE Transactions on Circuits and Systems, CAS-36, 1092, 10.1109/31.192419 Li, 1990, An optimized backpropagation with minimum norm weights, I, 697 Lippmann, 1987, An introduction to computing with neural nets, IEEE ASSP Magazine, 4, 10.1109/MASSP.1987.1165576 Papoulis, 1984 Rezgui, 1990, The effect of the slope of the activation function on the back propagation algorithm, I, 707 Rumelhart, 1986, Learning internal representation by error propagation, vol. 1, 318