arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.10352cs.LGcs.DS
收藏

矢量符号体系结构的容量分析

Capacity Analysis of Vector Symbolic Architectures

IBM Research(IBM研究院);University of California, Berkeley(加州大学伯克利分校)

Kenneth L. Clarkson, Shashanka Ubaru, Elizabeth Yang

摘要:

超维计算(Hyperdimensional Computing,HDC)是一种生物学启发的框架,它用高维向量表示符号,并使用向量操作来操纵它们。一个特定的向量空间和一组规定的向量运算(包括一个用于“捆绑”的加法和一个用于“绑定”的外积)的集合形成了一个 * 向量符号体系结构 *(VSA)。虽然VSAs已被用于许多应用中,并已进行了实证研究,许多关于VSAs的理论问题仍然是开放的。我们分析了四种常见的VSA:MAP-I,MAP-B和两种基于稀疏二进制向量的VSA的 * 表示能力 *。这里的“表示能力”指的是执行某些符号任务所需的VSA向量的维度上的界限,所述符号任务诸如测试集合成员资格$i \in S$和以给定的准确度估计两个符号集合$X$和$Y$的集合交集大小$|X \cap Y|$。我们还分析了Hopfield网络(一种简单的联想记忆模型)的一种新变体执行一些通常要求VSA的相同任务的能力。除了提供新的VSA能力的界限,我们的分析建立和利用VSA之间的连接,“草图”(降维)算法,和布隆过滤器。

英文摘要:

Hyperdimensional computing (HDC) is a biologically-inspired framework which represents symbols with high-dimensional vectors, and uses vector operations to manipulate them. The ensemble of a particular vector space and a prescribed set of vector operations (including one addition-like for "bundling" and one outer-product-like for "binding") form a *vector symbolic architecture* (VSA). While VSAs have been employed in numerous applications and have been studied empirically, many theoretical questions about VSAs remain open. We analyze the *representation capacities* of four common VSAs: MAP-I, MAP-B, and two VSAs based on sparse binary vectors. "Representation capacity' here refers to bounds on the dimensions of the VSA vectors required to perform certain symbolic tasks, such as testing for set membership $i \in S$ and estimating set intersection sizes $|X \cap Y|$ for two sets of symbols $X$ and $Y$, to a given degree of accuracy. We also analyze the ability of a novel variant of a Hopfield network (a simple model of associative memory) to perform some of the same tasks that are typically asked of VSAs. In addition to providing new bounds on VSA capacities, our analyses establish and leverage connections between VSAs, "sketching" (dimensionality reduction) algorithms, and Bloom filters.

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。

↑