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 2201.11691cs.AI
收藏

序列保相似超向量表示的递归绑定

Recursive Binding for Similarity-Preserving Hypervector Representations of Sequences

International Research and Training Center for Information Technologies and Systems(国际信息技术与系统研究培训中心);Luleå University of Technology(吕勒奥理工大学);University of California at Berkeley(加州大学伯克利分校);Research Institutes of Sweden(瑞典研究院)

Dmitri A. Rachkovskij, Denis Kleyko

摘要:

超维计算(Hypervidencial Computing,HDC),也称为向量符号架构(Vector Symbolic Architectures,VSA),是一种在人工智能和认知计算中使用的计算框架,它使用大的固定维度的分布式向量表示进行操作。设计HDC/VSA解决方案的关键步骤是从输入数据获得这种表示。在这里,我们专注于序列,并提出他们的变换,以分布式表示,既保持相同的序列元素在附近的位置的相似性,是等变的序列移位。通过使用递归绑定和叠加操作形成序列位置的表示来实现这些性质。建议的转换进行了实验研究与符号串用于建模人类感知的单词相似性。所获得的结果是在与更复杂的方法从文献中。所提出的变换是为HDC/VSA模型设计的,称为傅立叶全息简化表示。然而,它可以适应其他一些HDC/VSA模型。

英文摘要:

Hyperdimensional computing (HDC), also known as vector symbolic architectures (VSA), is a computing framework used within artificial intelligence and cognitive computing that operates with distributed vector representations of large fixed dimensionality. A critical step for designing the HDC/VSA solutions is to obtain such representations from the input data. Here, we focus on sequences and propose their transformation to distributed representations that both preserve the similarity of identical sequence elements at nearby positions and are equivariant to the sequence shift. These properties are enabled by forming representations of sequence positions using recursive binding and superposition operations. The proposed transformation was experimentally investigated with symbolic strings used for modeling human perception of word similarity. The obtained results are on a par with more sophisticated approaches from the literature. The proposed transformation was designed for the HDC/VSA model known as Fourier Holographic Reduced Representations. However, it can be adapted to some other HDC/VSA models.

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。

↑