Creating efficient nonlinear neural network process models that allow model interpretation

@article{Scott1993CreatingEN,
  title={Creating efficient nonlinear neural network process models that allow model interpretation},
  author={G. M. Scott and W. Ray},
  journal={Journal of Process Control},
  year={1993},
  volume={3},
  pages={163-178}
}
  • G. M. Scott, W. Ray
  • Published 1993
  • Computer Science
  • Journal of Process Control
  • Abstract The KBANN (knowledge-based artificial neural networks) approach uses neural networks to refine knowledge that can be written in the form of simple propositional rules. This idea is extended by presenting the MANNIDENT (multivariable artificial neural network identification) algorithm by which the mathematical equations of linear process models determine the topology and initial weights of a network, which is further trained using backpropagation. This method is applied to the task of… CONTINUE READING
    37 Citations

    Topics from this paper.

    Neural Network Process Models Based on Linear Model Structures
    • 4
    Recurrent neural networks for identification of nonlinear systems
    • X. Ren, S. Fei
    • Computer Science
    • Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187)
    • 2000
    • 3
    Recurrent neuro-fuzzy networks for nonlinear process modeling
    • 262
    Automated Recurrent Neural Network Design to Model the Dynamics of Complex Systems
    • 13
    • Highly Influenced
    Modelling Chaos with Neural Networks
    Constrained Hybrid Neural Modelling of Biotechnological Processes
    • 3