arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16620cs.LGcs.AI
收藏

超维向量Tsetlin机及其在序列学习与生成中的应用

Hyperdimensional Vector Tsetlin Machines with Applications to Sequence Learning and Generation

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

Christian D. Blakely

AI总结:

本文提出一种结合超维向量计算与Tsetlin机子句结构的两层模型,用于高效学习与生成序列数据,并在UCR时间序列分类等任务中展现出强竞争力。

摘要:

我们构建了一个用于学习和生成序列数据的两层模型,该模型计算速度快且与原始Tsetlin机相媲美,并增加了诸多优势。通过使用超维向量计算(HVC)代数和Tsetlin机子句结构,我们证明两者的结合继承了HVC数据编码与解码的通用性,以及Tsetlin机快速可解释的特性,从而产生了一个强大的机器学习模型。我们将该方法应用于两个领域,即预测、生成新序列和分类。对于后者,我们得出了整个UCR时间序列档案的结果,并与标准基准进行比较,以查看该方法在时间序列分类中的竞争力。

英文摘要:

We construct a two-layered model for learning and generating sequential data that is both computationally fast and competitive with vanilla Tsetlin machines, adding numerous advantages. Through the use of hyperdimensional vector computing (HVC) algebras and Tsetlin machine clause structures, we demonstrate that the combination of both inherits the generality of data encoding and decoding of HVC with the fast interpretable nature of Tsetlin machines to yield a powerful machine learning model. We apply the approach in two areas, namely in forecasting, generating new sequences, and classification. For the latter, we derive results for the entire UCR Time Series Archive and compare with the standard benchmarks to see how well the method competes in time series classification.

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。

↑