DocumentCode :
285178
Title :
Efficient algorithm for the design of multilayer feedforward neural networks
Author :
Tan, Shaohua ; Vandewalle, Joos
Author_Institution :
Dept. of Electr. Eng., Nat. Univ. of Singapore, Singapore
Volume :
2
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
190
Abstract :
A novel design technique that builds a multilayer feedforward net for an arbitrary set of binary associations is presented. The key to the technique is to decompose the arbitrary mapping into a sequence of operations composed of three primitive operations. As each of the primitive operations is easily realizable in a simple layered feedforward net, the mapping can be realized by cascading the simple feedforward nets corresponding to the decomposition. The time spent in the construction of the net is proportional to k×n 2, compared to k×2n typical of the conventional direct approaches. With such a reduction, the technique can be used in building multilayer feedforward nets for binary association problems of extremely large size
Keywords :
content-addressable storage; feedforward neural nets; arbitrary mapping; binary associations; decomposition; multilayer feedforward neural networks; Algorithm design and analysis; Buildings; Feedforward neural networks; Logic functions; Multi-layer neural network; Network topology; Neural networks; Neurons; Process design; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227009
Filename :
227009
Link To Document :
بازگشت