Optimal Brain Damage

Explore this paper's citation graph

Summary

A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.

Type
article
Published
1989-01-01
Cited by
5,404
References
17

Keywords

Computer science, Generalization, Artificial neural network, Class (philosophy), Artificial intelligence

References

Cited by

Related papers