arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.04255cs.AIcs.CLcs.IR
收藏

人工智能中的量子数学

Quantum Mathematics in Artificial Intelligence

IonQ, Inc.(IonQ 公司);University of Technology Sydney(悉尼科技大学);University of Washington(华盛顿大学)

Dominic Widdows, Kirsty Kitto, Trevor Cohen

摘要:

2010年以来的十年,人工智能的成功一直处于计算机科学技术的前沿,向量空间模型也巩固了在人工智能前沿的地位。与此同时,量子计算机变得更加强大,重大进展的公告经常出现在新闻中。这两个领域的数学技术有更多的共同点比有时意识到的。向量空间在20世纪30年代占据了量子力学公理化的核心地位,这种采用是从向量空间的线性几何推导逻辑和概率的关键动机。粒子之间的量子相互作用使用张量积来建模,张量积也用于表达人工神经网络中的对象和操作。本文描述了其中一些常见的数学领域,包括它们如何用于人工智能(AI)的例子,特别是在自动推理和自然语言处理(NLP)。讨论的技术包括向量空间,标量积,子空间和蕴涵,正交投影和否定,对偶向量,密度矩阵,正算子和张量积。应用领域包括信息检索、分类和含义、建模词义和消歧、知识库中的推理和语义组合。其中一些方法可能会在量子硬件上实现。执行工作中的许多实际步骤还处于早期阶段,有些已经实现。解释一些常见的数学工具可以帮助人工智能和量子计算的研究人员进一步利用这些重叠,识别和探索新的方向。

英文摘要:

In the decade since 2010, successes in artificial intelligence have been at the forefront of computer science and technology, and vector space models have solidified a position at the forefront of artificial intelligence. At the same time, quantum computers have become much more powerful, and announcements of major advances are frequently in the news. The mathematical techniques underlying both these areas have more in common than is sometimes realized. Vector spaces took a position at the axiomatic heart of quantum mechanics in the 1930s, and this adoption was a key motivation for the derivation of logic and probability from the linear geometry of vector spaces. Quantum interactions between particles are modelled using the tensor product, which is also used to express objects and operations in artificial neural networks. This paper describes some of these common mathematical areas, including examples of how they are used in artificial intelligence (AI), particularly in automated reasoning and natural language processing (NLP). Techniques discussed include vector spaces, scalar products, subspaces and implication, orthogonal projection and negation, dual vectors, density matrices, positive operators, and tensor products. Application areas include information retrieval, categorization and implication, modelling word-senses and disambiguation, inference in knowledge bases, and semantic composition. Some of these approaches can potentially be implemented on quantum hardware. Many of the practical steps in this implementation are in early stages, and some are already realized. Explaining some of the common mathematical tools can help researchers in both AI and quantum computing further exploit these overlaps, recognizing and exploring new directions along the way.

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。

↑