Title :
On the representation of data for optimal learning
Author :
ter Brugge, M.H. ; Nijhuis, J.A.G. ; Jansen, W.J. ; Drenth, H. ; Spaanenburg, L.
Author_Institution :
Dept. of Comput. Sci., Groningen Univ., Netherlands
Abstract :
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
Keywords :
data structures; fault diagnosis; learning (artificial intelligence); neural nets; welding; data representation; data screening; learning set; neural networ training; nondestructive ultrasonic diagnosis; optimal learning; precoder; spot welds; target network topology; Assembly; Classification tree analysis; Data engineering; Feedforward neural networks; Learning systems; Network topology; Neural networks; Neurofeedback; Neurons; Spot welding;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487294
