arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.03100cs.AIcs.LGstat.ML
收藏

将学习规则与表示分离

Decoupling Learning Rules from Representations

Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学)

Philip S. Thomas, Christoph Dann, Emma Brunskill

摘要:

在人工智能领域,学习通常对应于改变参数化函数的参数。学习规则是一种算法或数学表达式,它精确地规定了参数应该如何改变。在创建人工智能系统时,我们必须做出两个决定:应该使用什么表示(即,应该使用什么参数化函数)以及应该使用什么学习规则来搜索可表示函数的结果集。使用大多数学习规则,这两个决定以一种微妙的(通常是无意的)方式耦合在一起。也就是说,使用相同的学习规则和可以表示相同函数集的两种不同表示可以导致两种不同的结果。在认为这种耦合是不可取的,特别是当使用人工神经网络,我们提出了一种方法,部分解耦这两个决策的广泛的学习规则,跨越无监督学习,强化学习,和监督学习。

英文摘要:

In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating an artificial intelligence system, we must make two decisions: what representation should be used (i.e., what parameterized function should be used) and what learning rule should be used to search through the resulting set of representable functions. Using most learning rules, these two decisions are coupled in a subtle (and often unintentional) way. That is, using the same learning rule with two different representations that can represent the same sets of functions can result in two different outcomes. After arguing that this coupling is undesirable, particularly when using artificial neural networks, we present a method for partially decoupling these two decisions for a broad class of learning rules that span unsupervised learning, reinforcement learning, and supervised learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑