Multi-layer Perceptron on Interval Data ?

We study in this paper several methods that allow one to use interval data as inputs for Multi-layer Perceptrons. We show that interesting results can be obtained by using together two methods: the extremal values method which is based on a complete description of intervals, and the simulation method which is based on a probabilistic understanding of intervals. Both methods can be easily implemented on top of existing neural network software.

[1]  S. J. Simoff.  Handling uncertainty in neural networks: an interval approach , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[2]  Yves Grandvalet,et al.  Noise Injection: Theoretical Prospects , 1997, Neural Computation.

[3]  Jirí Síma,et al.  Neural expert systems , 1995, Neural Networks.

[4]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[5]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[6]  Christopher M. Bishop,et al.  Current address: Microsoft Research, , 2022 .

[7]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[8]  Hans-Hermann Bock,et al.  Analysis of Symbolic Data , 2000 .

[9]  Hans-Hermann Bock,et al.  Analysis of Symbolic Data: Exploratory Methods for Extracting Statistical Information from Complex Data , 2000 .

[10]  Chenyi Hu,et al.  On interval weighted three-layer neural networks , 1998, Proceedings 31st Annual Simulation Symposium.