IEEE Transactions on Neural Networks · 1999 · 98 citations · 14 references
ComputingComputer ScienceAlgorithmsMachine LearningOptimizationNeural NetworksNonlinear ProgrammingOptimization For Machine LearningNonlinear Network OptimizationNonlinear OptimizationOptimization AlgorithmsWeight Initialization
Conventional neural-network training algorithms often get stuck in local minima. To find the global optimum, training is conventionally repeated with ten, or so, random starting values for the weights. Here we develop an analytical procedure to determine how many times a neural network needs to be trained, with random starting weights, to ensure that the best of those is within a desirable lower percentile of all possible trainings, with a certain level of confidence. The theoretical developments are validated by experimental results. While applied to neural-network training, the method is generally applicable to nonlinear optimization.
14
Neural networks: A comprehensive foundation
Ryszard Tadeusiewicz · Control Engineering Practice · 1995 · 7.3K citations
Pattern Classification and Scene Analysis
Michael Thompson, Richard O. Duda, Peter E. Hart · Leonardo · 1974 · 4.5K citations
Modeling chemical process systems via neural computation
N. Bhat, Peter A. Minderman, Thomas J. McAvoy et al. · IEEE Control Systems Magazine · 1990 · 250 citations