On the representation of data for optimal learning
暂无分享,去创建一个
The key to the successful training of a neural network lies in the careful composition of the learning set. A simple method of data screening is described to verify conformance with the restrictions imposed by the target network topology and ensuing applied to the nondestructive ultrasonic diagnosis of spot welds. It is illustrated how such a screening may indicate the suitability of a learning set before application to the neural net and therefore aids in designing a proper precoder.
[1] Yagmur Denizhan,et al. Classification trees prove useful in nondestructive testing of spot weld quality , 1993 .
[2] Etienne Barnard,et al. Invariance and neural nets , 1991, IEEE Trans. Neural Networks.
[3] Sung-Jin Song,et al. Ultrasonic flaw classification in weldments using probabilistic neural networks , 1992 .
[4] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.