arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.09488cs.LGcs.AI
收藏

关于AND和OR算子的Tsetlin机的收敛性

On the Convergence of Tsetlin Machines for the AND and the OR Operators

University of Agder(阿格德大学);Centre for Artificial Intelligence Research(人工智能研究中心);Norwegian Research Centre (NORCE)(挪威研究中心(NORCE))

Lei Jiao, Xuan Zhang, Ole-Christoffer Granmo

摘要:

Tsetlin机(TM)是一种基于命题逻辑的新型机器学习算法,在若干模式识别问题上取得了较好的性能。在以前的研究中,TM的收敛性能进行了分析1位操作和异或操作。为了使对基本数字运算的分析更加完整,本文分析了输入训练样本分别跟随AND和OR运算符时的收敛性。我们的分析表明,TM几乎可以肯定地收敛到复制AND和OR算子,这是从训练数据在无限的时间范围内学习。对AND和OR运算的分析,加上前面分析的1位运算和XOR运算,完成了布尔代数基本运算的收敛性分析。

英文摘要:

The Tsetlin Machine (TM) is a novel machine-learning algorithm based on propositional logic, which has obtained state-of-the-art performance on several pattern recognition problems. In previous studies, the convergence properties of TM for 1-bit operation and XOR operation have been analyzed. To make the analyses for the basic digital operations complete, in this article, we analyze the convergence when input training samples follow AND and OR operators respectively. Our analyses reveal that the TM can converge almost surely to reproduce AND and OR operators, which are learnt from training data over an infinite time horizon. The analyses on AND and OR operators, together with the previously analysed 1-bit and XOR operations, complete the convergence analyses on basic operators in Boolean algebra.

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。

↑