Title :
On linear programming, neural network design, pattern classification and polynomial time training
Author_Institution :
Dept. of Decision & Inf. Syst., Coll. of Bus., Arizona State Univ., Tempe, AZ, USA
fDate :
30 Aug-3 Sep 1992
Abstract :
Polynomial time training and network design are two major issues for the neural network community. A new algorithm has been developed that can both `design´ an appropriate network and `train´ it in polynomial time. The algorithm is for classification problems and uses linear programming formulations in designing and training the network. This paper summarizes the new algorithm
Keywords :
computational complexity; image recognition; learning systems; linear programming; neural nets; polynomials; computational complexity; design; learning systems; linear programming; neural network; pattern classification; pattern recognition; polynomial time training; Linear programming; Neural networks; Pattern classification; Polynomials; Vectors;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201709
