gpt4 book ai didi

machine-learning - 直接或间接的培训经验类型

转载 作者:行者123 更新时间:2023-11-30 08:44:23 25 4
gpt4 key购买 nike

我有一个问题,

在机器学习中,我们为训练体验类型定义了两种类型:

直接和间接。

我搜索了很多关于差异的信息,但我找不到。有人熟悉这些吗?

提前谢谢

最佳答案

在他的书中"Machine Learning" (1st ed.) ,Tom Mitchell 解释如下(参见第 5 页第 1.2.1 节):

For example, in learning to play checkers, the system might learn from direct training examples consisting of individual checkers board states and the correct move for each. Alternatively, it might have available only indirect information consisting of the move sequences and final outcomes of various games played. In this later case, information about the correctness of specific moves early in the game must be inferred indirectly from the fact that the game was eventually won or lost.

他进一步指出:

Here [using indirect feedback] the learner faces an additional problem of credit assignment, or determining the degree to which each move in the sequence deserves credit or blame for the final outcome. Credit assignment can be a particularly difficult problem because the game can be lost even when early moves are optimal, if these are followed later by poor moves. Hence, learning from direct training feedback is typically easier than learning from indirect feedback.

关于machine-learning - 直接或间接的培训经验类型,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/25815299/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com