arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1510.03370cs.LGcs.AI
收藏

渐近逻辑不确定性与Benford检验

Asymptotic Logical Uncertainty and The Benford Test

University of California Los Angeles(加州大学洛杉矶分校);Machine Intelligence Research Institute(机器智能研究所);University of Southern California(南加州大学)

Scott Garrabrant, Siddharth Bhaskar, Abram Demski, Joanna Garrabrant, George Koleszarik, Evan Lloyd

摘要:

我们给出一个算法A,它分配概率的逻辑句子。对于任何简单的无限序列的句子,其真值看起来与以概率p输出“真”的有偏硬币不可区分,我们有A赋予这些句子的概率序列收敛于p。

英文摘要:

We give an algorithm A which assigns probabilities to logical sentences. For any simple infinite sequence of sentences whose truth-values appear indistinguishable from a biased coin that outputs "true" with probability p, we have that the sequence of probabilities that A assigns to these sentences converges to p.

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。

↑