A Simple Procedure for Pruning Back-Propagation Trained Neural Networks

IEEE Transactions on Neural Networks

Volumn 1, Issue 2, 1990, Pages 239-242

  Karnin, Ehud D ^a  

^a IBM HAIFA RESEARCH LAB   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; COST FUNCTIONS; GLOBAL ERROR FUNCTIONS;

SYSTEMS SCIENCE AND CYBERNETICS;

EID: 0025447562     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.80236     Document Type: Letter

References (5)

1. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing, vol. 1, D. E. Rumelhart and J. L. McCleland, Eds. Cambridge, MA: M.I.T. Press, 1986, pp. 318-362.
2. D. G. Luenberger, Linear and Nonlinear Programming. Reading, MA: Addison-Wesley, 1984.
3. J. Sietsma and R. J. F. Dow, “Neural net pruning—Why and how?,” in Proc. IEEE Int. Conf. Neural Networks, vol. 1 ‘San Diego, CA’, 1988, pp. 325-332.
4. S. J. Hanson and L. Y. Pratt, “Comparing biases for minimal network construction with backpropagation,” in Advances in Neural Information Processing I, D. S. Touretzky, Ed. Morgan Kaufmann, 1989, pp. 177-185.
5. M. C. Mozer and P. Smolensky, “Skeletonization: A technique for trimming the fat from a network via relevance assessment,” in Advances in Neural Information Processing I, D. S. Touretzky, Ed. Morgan Kaufmann, 1989, pp. 107-115.