arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2203.07975cs.LGcond-mat.dis-nncs.AImath.AGmath.CTmath.DG
收藏

算法分类器的类别表示学习和RG流算子

Categorical Representation Learning and RG flow operators for algorithmic classifiers

Harvard University(哈佛大学);University of Miami(迈阿密大学);National Research University Higher School of Economics(国立研究型大学高等经济学院);University of California San Diego(加州大学圣地亚哥分校);QGNai INC.(QGNai公司)

Artan Sheshmani, Yizhuang You, Wenbo Fu, Ahmadreza Azizi

摘要:

在前两位作者的范畴表示学习(arXiv:2103.14770)的早期形式化之后,我们讨论了“基于RG流的范畴化器”的构造。借鉴量子场论中的重整化群流(RG)理论、全息对偶和双曲几何的思想,并将其与神经ODE相结合,我们构建了一个新的算法自然语言处理(NLP)架构,称为RG流分类器或简称RG分类器,它能够在所有层中进行数据分类和生成。我们将我们的算法平台应用于生物医学数据集,并展示了其在序列到功能映射领域的性能。特别是,我们将RG分类器应用于流感病毒的特定基因组序列,并展示了我们的技术如何能够从给定的基因组序列中提取信息,找到它们隐藏的对称性和主要特征,对它们进行分类,并使用训练数据对与新病毒集相关的新的合理生成序列进行随机预测,这些新病毒可以避免人类免疫系统。当前文章的内容是前两位作者最近提交的美国专利申请的一部分(美国专利申请号:63/313.504)。

英文摘要:

Following the earlier formalism of the categorical representation learning (arXiv:2103.14770) by the first two authors, we discuss the construction of the "RG-flow based categorifier". Borrowing ideas from theory of renormalization group flows (RG) in quantum field theory, holographic duality, and hyperbolic geometry, and mixing them with neural ODE's, we construct a new algorithmic natural language processing (NLP) architecture, called the RG-flow categorifier or for short the RG categorifier, which is capable of data classification and generation in all layers. We apply our algorithmic platform to biomedical data sets and show its performance in the field of sequence-to-function mapping. In particular we apply the RG categorifier to particular genomic sequences of flu viruses and show how our technology is capable of extracting the information from given genomic sequences, find their hidden symmetries and dominant features, classify them and use the trained data to make stochastic prediction of new plausible generated sequences associated with new set of viruses which could avoid the human immune system. The content of the current article is part of the recent US patent application submitted by first two authors (U.S. Patent Application No.: 63/313.504).

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。

↑