2009 · 36 citations · 8 references
ComputingComputer ScienceMachine LearningNeural EngineeringTraining SystemsAdaptive LearningDeep LearningNeural NetworksBackpropagationConvergenceFeedforward Neural NetworksLearningMultilayer PerceptronNeural Network Prediction
In this paper, a new back propagation (BP) algorithm with adaptive momentum is proposed, where the momentum coefficient is adjusted iteratively based on the current descent direction and the weight increment in the last iteration. A convergence result of the algorithm is presented when it is used for training feed forward neural networks (FNNs) with a hidden layer. Simulation results have shown that this new algorithm has a distinct superiority in fast convergence and smoothing oscillation over the conventional BP method. Moreover, the range for the learning rate has been widened after the inclusion of such an adaptable momentum while maintaining the stability of networks.
8
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
The need for small learning rates on large problems
D.R. Wilson, Tony Martinez · 2002 · 139 citations