计算机科学
一般化
人工神经网络
班级(哲学)
人工智能
集合(抽象数据类型)
机器学习
数学优化
算法
数学
数学分析
程序设计语言
作者
Yann LeCun,John S. Denker,Sara A. Solla
摘要
We have used information-theoretic ideas to derive a class of practical and nearly optimal schemes for adapting the size of a neural network. By removing unimportant weights from a network, several improvements can be expected: better generalization, fewer training examples required, and improved speed of learning and/or classification. The basic idea is to use second-derivative information to make a tradeoff between network complexity and training set error. Experiments confirm the usefulness of the methods on a real-world application.
科研通智能强力驱动
Strongly Powered by AbleSci AI