Reed R
Dept. of Electr. Eng., Washington Univ., Seattle, WA.
IEEE Trans Neural Netw. 1993;4(5):740-7. doi: 10.1109/72.248452.
A rule of thumb for obtaining good generalization in systems trained by examples is that one should use the smallest system that will fit the data. Unfortunately, it usually is not obvious what size is best; a system that is too small will not be able to learn the data while one that is just big enough may learn very slowly and be very sensitive to initial conditions and learning parameters. This paper is a survey of neural network pruning algorithms. The approach taken by the methods described here is to train a network that is larger than necessary and then remove the parts that are not needed.
在通过示例训练的系统中，获得良好泛化能力的一个经验法则是使用能够拟合数据的最小系统。不幸的是，通常并不清楚最佳的系统规模是多少；太小的系统无法学习数据，而规模刚好足够大的系统可能学习速度非常慢，并且对初始条件和学习参数非常敏感。本文是对神经网络剪枝算法的综述。这里描述的方法所采取的途径是训练一个比所需规模更大的网络，然后去除不需要的部分。
