arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.04771cs.LGcs.AIcs.NE
收藏

用于MBAT矢量符号结构的正交矩阵和用于JSON的“软”VSA表示

Orthogonal Matrices for MBAT Vector Symbolic Architectures, and a "Soft" VSA Representation for JSON

Textician(Textician 公司)

Stephen I. Gallant

摘要:

向量符号体系结构(VSAs)提供了一种将复杂对象表示为单个固定长度向量的方法,以便相似的对象具有相似的向量表示。这些向量表示然后变得易于用于机器学习或最近邻搜索。我们回顾了以前提出的VSA方法,MBAT(矩阵绑定的加法项),它使用随机矩阵的乘法绑定相关的条款。然而,乘以这样的矩阵引入了可能损害性能的不稳定性。使随机矩阵成为正交矩阵可证明地解决了这个问题。对于更大规模的应用程序,我们看到了如何将MBAT向量表示应用于任何以JSON表示的数据。JSON在许多程序设计语言中用于表达复杂的数据,但其原生格式似乎非常不适合机器学习。将JSON表示为固定长度的向量,使其易于用于机器学习和最近邻搜索。创建这样的JSON向量还表明,VSA需要采用非交换的绑定操作。VSA现在已经准备好尝试全面的实际应用,包括医疗保健,制药和基因组学。保留字:MBAT(Matrix Binding of Additive Terms),VSA(Vector Symbolic Architecture),HDC(Hyperdimensional Computing),分布式表示,绑定,正交矩阵,递归连接,机器学习,搜索,JSON,VSA应用

英文摘要:

Vector Symbolic Architectures (VSAs) give a way to represent a complex object as a single fixed-length vector, so that similar objects have similar vector representations. These vector representations then become easy to use for machine learning or nearest-neighbor search. We review a previously proposed VSA method, MBAT (Matrix Binding of Additive Terms), which uses multiplication by random matrices for binding related terms. However, multiplying by such matrices introduces instabilities which can harm performance. Making the random matrices be orthogonal matrices provably fixes this problem. With respect to larger scale applications, we see how to apply MBAT vector representations for any data expressed in JSON. JSON is used in numerous programming languages to express complex data, but its native format appears highly unsuited for machine learning. Expressing JSON as a fixed-length vector makes it readily usable for machine learning and nearest-neighbor search. Creating such JSON vectors also shows that a VSA needs to employ binding operations that are non-commutative. VSAs are now ready to try with full-scale practical applications, including healthcare, pharmaceuticals, and genomics. Keywords: MBAT (Matrix Binding of Additive Terms), VSA (Vector Symbolic Architecture), HDC (Hyperdimensional Computing), Distributed Representations, Binding, Orthogonal Matrices, Recurrent Connections, Machine Learning, Search, JSON, VSA Applications

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。

↑