将记忆与程序融合，用函数表示法重构计算模型
The Function-Representation Model of Computation
- 提出函数表示法：内存与程序统一的新型计算模型
- 数学证明该模型可实现多种函数，支持多实例组织
- 适合研究人工认知架构与计算范式创新的学者
认知架构是人工认知研究的前沿方向，但其基于分离的存储与程序计算模型，存在知识检索启发式难题。本文提出一种新计算模型——函数表示法，将记忆与程序融合。该模型通过定义通用函数表示法并实例化多个实例来实现计算。本文通过数学定义与证明，探索该模型的潜力，分析其可实现的函数类型，并提出多种函数表示法实例的组织方式。
原文摘要 · Abstract (English)
Cognitive Architectures are the forefront of the research into developing an artificial cognition. However, they approach the problem from a separated memory and program model of computation. This model of computation poses a fundamental problem: the knowledge retrieval heuristic. In this paper we propose to solve this problem by using a novel model of computation, one where memory and program are merged: the Function-Representation. This model of computation involves defining a generic Function-Representation and instantiating multiple instances of it. In this paper we explore the potential of this novel model of computation through mathematical definitions and proofs. We also explore the kind of functions a Function-Representation can implement, and present different ways to organise multiple instances of a Function-Representation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。