Corpus ID: 18278557

Explanation of feedforward Neural Networks through sensibility analysis

@inproceedings{NarazakiExplanationOF,
  title={Explanation of feedforward Neural Networks through sensibility analysis},
  author={Hiroshi Narazaki and Toshihiko Watanabe and Masaki Yamamoto}
}
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… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 12 REFERENCES
Reorganizing knowledge in neural networks: an explanatory mechanism for neural networks in data classification problems
TLDR
This paper proposes a method that reorganizes the distributed knowledge in the NN to extract approximate classification rules and divides the input space into "monotonic regions" where a monotonic region is a set of input patterns that belongs to the same class with the same sensitivity pattern. Expand
Fuzzy and neural approaches in engineering
From the Publisher: Fuzzy and Neural Approaches in Engineering presents a detailed examination of the fundamentals of fuzzy systems and neural networks and then joins them synergistically -Expand
Neural Networks for Pattern Recognition
TLDR
The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue. Expand
Fuzzy logic systems for engineering: a tutorial
A fuzzy logic system (FLS) is unique in that it is able to simultaneously handle numerical data and linguistic knowledge. It is a nonlinear mapping of an input data (feature) vector into a scalarExpand
Fuzzy systems and fuzzy expert control: An overview
TLDR
This paper presents an overview of fuzzy set theory and its application to the analysis and design of fuzzy expert control systems, and a survey of the theoretical results and applications gives a good picture of the current status of the field. Expand
Neural Networks: A Comprehensive Foundation
TLDR
Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Expand
Fuzzy logic = computing with words
  • L. Zadeh
  • Computer Science
  • IEEE Trans. Fuzzy Syst.
  • 1996
TLDR
The point of this note is that fuzzy logic plays a pivotal role in CW and vice-versa and, as an approximation, fuzzy logic may be equated to CW. Expand
An incipient detection system based on the probabilistic radial basis function network: Application to the diagnosis of the condenser of a coal power plant
  • Neurocomputing
  • 1998
Sanz-Bobi, An incipient detection system based on the probabilistic radial basis function network: Application to the diagnosis of the condenser of a coal power plant
  • Neurocomputing 23,
  • 1998
Bishop . Neural Networks for Pattern Recognition
  • 1995
...
1
2
...