Hey Pentti, We Did (More of) It!: A Vector-Symbolic Lisp With Residue Arithmetic
Connor Hanley, Eilene Tomkins-Flanaganm, and Mary Alexandria Kelly
使用频率域全息减小表示(FHRR),我们将Lisp 1.5的矢量符号架构(VSA)编码与使用剩余超维计算(RHC)的算术运算为正文扩展。 在高维向量空间上编码图灵完备的语法会增加神经网络状态的表达性,使网络状态能够包含具有固有可解释的任意结构化表示。 我们讨论了VSA编码在机器学习任务中的潜在应用,以及编码结构化表示和设计神经网络的重要性,这些神经网络的行为因其获得比目前更通用的智能代理而对其表示结构敏感。
Using Frequency-domain Holographic Reduced Representations (FHRRs), we extend a Vector-Symbolic Architecture (VSA) encoding of Lisp 1.5 with primitives for arithmetic operations using Residue Hyperdimensional Computing (RHC). Encoding a Turing-complete syntax over a high-dimensional vector space increases the expressivity of neural network states, enabling network states to contain arbitrarily structured representations that are inherently interpretable. We discuss the potential applications of ...
