IEEE Transactions on Neural Networks · 1992 · 109 citations · 13 references
ComputingComputer ScienceComputer NetworksMachine LearningOptimizationError-based LearningNeural NetworksBackpropagationFeedforward Neural NetworksMultilayer Perceptron
It is shown theoretically that for an arbitrary T-element training set with t(t=/<T) different inputs, the backpropagation error surface does not have suboptimal local minima if the network is capable of exactly implementing an arbitrary training set consisting of t different patterns. 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.
13
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., WhiteH. · Neural Networks · 1989 · 9.4K citations
Theory of the backpropagation neural network
Hecht-Nielsen · 1989 · 2.2K citations
On the capabilities of multilayer perceptrons
Eric B. Baum · Journal of Complexity · 1988 · 380 citations