Summary: 242 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 1, NO. 2, JUNE 1990
T= 1 A B C D
 D. G . Luenberger, Linear and Nonlinear Programming. Reading,
MA: Addison-Wesley, 1984.
 J. Sietsma and R. J. F. Dow, "Neural net pruning-Why and how?,"
in Proc. IEEE Int. Con$ Neural Networks, vol. 1 (San Diego, CA),
1988, pp. 325-332.
 S. J. Hanson and L. Y,Pratt, "Comparing biases for minimal network
construction with back-propagation," in Advances in Neural Infor-
mation Processing I , D. S. Touretzky,Ed. MorganKaufmann, 1989,
(51 M. C. Mozer and P. Smolensky, "Skeletonization: A technique for
trimming the fat from a network via relevance assessment," in Ad-
vances in Neural Information Processing I , D. S. Touretzky, Ed.
Morgan Kaufmann, 1989, pp. 107-115.
Fig. 4. A network for the "rule-plus-exception" problem.
Neural Networks for Control Systems
PANOS J. ANTSAKLIS, SENIOR MEMBER, IEEE
were estimated during course of leaming were: