Title :
Rule extraction from neural networks by interval propagation
Author :
Palade, Vasile ; Neagu, Daniel-Ciprian ; Puscasu, Gheorghe
Author_Institution :
Sch. of Electr. Eng., Univ. of Galati, Romania
Abstract :
This paper proposes a method of rule extraction from ordinary backpropagation neural networks, which do not have a structure that facilitates rule extraction. This method is based on interval propagation across the network. The method of rule extraction uses a procedure for inverting a neural network, which is also presented. A common benchmark control problem was used to test the rule extraction and inversion methods
Keywords :
backpropagation; neural nets; backpropagation neural networks; benchmark control problem; interval propagation; neural network inversion; rule extraction; Backpropagation; Benchmark testing; Computer networks; Electronic mail; Fuzzy logic; Fuzzy neural networks; Medical diagnosis; Neural networks; Process control; Speech recognition;
Conference_Titel :
Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on
Conference_Location :
Brighton
Print_ISBN :
0-7803-6400-7
DOI :
10.1109/KES.2000.885796
