TY - GEN
T1 - A Polynomial Time Algorithm for Generating Neural Networks for Classification Problems
AU - Roy, Asim
AU - Mukhopadhyay, Somnath
N1 - Funding Information:
This research was supported by the National Science Foundation grant IRI-9113370.
Publisher Copyright:
© 1992 IEEE.
PY - 1992
Y1 - 1992
N2 - This paper presents a new polynomial time algorithm for the construction and training of multilayer perceptrons for classification problems. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven and computational results are provided for some well-known problems. In all cases, very small nets were created compared to those reported so far.
AB - This paper presents a new polynomial time algorithm for the construction and training of multilayer perceptrons for classification problems. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven and computational results are provided for some well-known problems. In all cases, very small nets were created compared to those reported so far.
UR - http://www.scopus.com/inward/record.url?scp=85132031294&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85132031294&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.1992.287225
DO - 10.1109/IJCNN.1992.287225
M3 - Conference contribution
AN - SCOPUS:85132031294
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 147
EP - 152
BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Y2 - 7 June 1992 through 11 June 1992
ER -