IEEE Transactions on Neural Networks · 1994 · 127 citations · 9 references
ComputingComputer ScienceAlgorithmsDynamical SystemsMachine LearningNeural ModelingNeural NetworksNeural System ModelingPattern RecognitionState-space ModelingState-space ModelsError PredictionNeural Dynamical SystemsNeural Network ModelingNeural Network PredictionNeural Noise ModelingRecurrent Neural Networks
The paper first summarizes a general approach to the training of recurrent neural networks by gradient-based algorithms, which leads to the introduction of four families of training algorithms. Because of the variety of possibilities thus available to the "neural network designer," the choice of the appropriate algorithm to solve a given problem becomes critical. We show that, in the case of process modeling, this choice depends on how noise interferes with the process to be modeled; this is evidenced by three examples of modeling of dynamical processes, where the detrimental effect of inappropriate training algorithms on the prediction error made by the network is clearly demonstrated.
9
Numerical recipes in C: the art of scientific computing
Choice Reviews Online · 1993 · 18.1K citations · Full text
<i>Numerical Recipes, The Art of Scientific Computing</i>
William H. Press, Brian P. Flannery, Saul A. Teukolsky et al. · American Journal of Physics · 1987 · 10.1K citations
Numerical Recipes: The Art of Scientific Computing
Eric R. Ziegel, William H. Press, Brian P. Flannery et al. · Technometrics · 1987 · 4.6K citations
Convergence Conditions for Ascent Methods
Philip Wolfe · SIAM Review · 1969 · 1.1K citations