Uncertainty Analysis Applied to Feedforward Neural Networks1

@article{Hess2007UncertaintyAA,
  title={Uncertainty Analysis Applied to Feedforward Neural Networks1},
  author={D. Hess and R. Roddy and W. Faller},
  journal={Ship Technology Research},
  year={2007},
  volume={54},
  pages={114 - 124}
}
Abstract Three problems associated with uncertainty in feedforward neural network predictions are discussed. First, the uncertainty present in the input vector propagates through a trained network into the output vector, and this uncer- tainty is determined using the matrix of partial derivatives defining the change in each output with respect to the inputs. Second, because the partial derivative information conveys the relative sensitivity of a given output to each of the inputs, it can be… Expand

References

SHOWING 1-9 OF 9 REFERENCES
Uncertainty Analysis Applied to Feedforward Neural Networks1
Neural network predictions of the 4-quadrant Wageningen B-screw series
  • 5th Int. Conf. Computer and IT Applications in the Maritime Industries,
  • 2006
Intelligent Calculation of Equations (ICE) User Manual, Applied Simulation Technologies, Cocoa
  • 2005
Experimentation and Uncertainty Analysis for Engineers, 2nd Ed.
Intelligent Calculation of Equations (ICE) User Manual, Applied Simulation Technologies
  • Uncertainty analysis applied to feedforward neural networks, 5 th Int. Conf. Computer and IT Applications in the Maritime Industries
  • 1999
Using Uncertainty Analysis in the Planning of an Experiment