2000 · 350 citations · 11 references
ComputingComputer ScienceAlgorithmsArtificial IntelligenceMachine LearningNeural NetworksOptimization For Machine LearningPattern RecognitionRepresentation LearningError SurfacesFast LearningOptimization AlgorithmsRadial Basis Function Networks
The Rprop algorithm proposed by Riedmiller and Braun is one of the best performing first-order learning methods for neural networks. We introduce modifications of the algorithm that improve its learning speed. The resulting speedup is experimentally shown for a set of neural network learning tasks as well as for artificial error surfaces.
11
Increased rates of convergence through learning rate adaptation
Robert A. Jacobs · Neural Networks · 1988 · 1.8K citations
Yann LeCun, Léon Bottou, Genevieve Orr et al. · Neural Information Processing Systems · 1998 · 1.4K citations
Accelerating the convergence of the back-propagation method
Thomas P. Vogl, J. K. Mangis, A. K. Rigler et al. · Biological Cybernetics · 1988 · 1.1K citations