Can backpropagation error surface not have local minima
Can backpropagation error surface not have local minima is a scholarly work, published in 1992 in ''IEEE Transactions on Neural Networks''. The main subjects of the publication include extreme learning machine, maxima and minima, backpropagation, set, surface, computer science, algorithm, field-programmable gate array, mathematics, artificial neural network, and artificial intelligence. As a special case, the error surface of a backpropagation network with one hidden layer and t-1 hidden units has no local minima, if the network is trained by an arbitrary T-element set with t different inputs.