• Plataforma de vídeos del IIT
  • Twitter
  • LinkedIn
  • Asociación de Ingenieros del ICAI
  • Intranet
  • English
Ir arriba
Información del artículo en conferencia

Explanation of feedforward Neural Networks through sensibility analysis

J. Besada, M.A. Sanz-Bobi

NNA '01, International Conference on Neural Networks and Applications, pp. 384-391, Tenerife (España). 11 febrero 2001


Resumen:
This paper proposes a new method for explanation of trained neural networks feed forward type. The new knowledge collected is expressed by fuzzy rules directly from a sensibility analysis inputs/outputs to the neural network. This easy extraction is based on the properties of the derivative of a tangent hyperbolic function used as activation function in the hidden layer of the neural network. The analysis performed is very useful not only for extraction of knowledge, but to know the importance of every rule extracted in the whole knowledge and, also, the importance of every input stimulating the network. An example based on a real case shows the goal properties of the new method proposed.


Palabras clave: Neural Networks, Neuro-fuzzy models, rule extraction, sensibility analysis, knowledge discovering.


Fecha de publicación: febrero 2001.



Cita:
J. Besada, M.A. Sanz-Bobi, Explanation of feedforward Neural Networks through sensibility analysis, NNA '01, International Conference on Neural Networks and Applications, pp. 384-391, Tenerife (España). 11-15 Febrero 2001.

IIT-00-041A

pdf Solicitar el artículo completo a los autores