标签:深度学习 its erro gen mod training int error 算法
在深度学习中,许多策略可以减少测试误差,可能以增加训练误差为代价,这些策略统一称为正则化。
在《deep learning》中,正则化被定义为 ‘any modification we make to a learning algorithm that is intended to reduce its generalization error but not its training error.’ (对学习算法的修改--旨在减少泛化误差而非训练误差)
标签:深度学习 its erro gen mod training int error 算法
原文地址:http://www.cnblogs.com/max-hu/p/7103891.html