Title :
Inventory control neural network system
Author :
Ezziane, Z.H. ; Mazouz, A.K. ; Han, C.
Author_Institution :
Florida Atlantic Univ., Baca Raton, FL, USA
Abstract :
A two-layer perceptron feedforward backpropagation network architecture with a minimum number of hidden neurons is designed using the backpropagation training algorithm for a noncomplex application, namely, controlling a plant inventory system. The design objective is to determine the number of hidden neurons and what type of data must be entered to get the backpropagation algorithm started. The convergence of the algorithm within a reasonable amount of time is sought. Test results are promising
Keywords :
backpropagation; convergence; feedforward neural nets; industrial control; industrial plants; multilayer perceptrons; stock control; backpropagation training algorithm; convergence; feedforward; hidden neurons; neural network system; plant inventory system; two-layer perceptron; Backpropagation algorithms; Convergence; Flow production systems; Inventory control; Neural networks; Neurons; Pattern recognition; Production facilities; Raw materials; Unsupervised learning;
Conference_Titel :
System Theory, 1993. Proceedings SSST '93., Twenty-Fifth Southeastern Symposium on
Conference_Location :
Tuscaloosa, AL
Print_ISBN :
0-8186-3560-6
DOI :
10.1109/SSST.1993.522779
