arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09823cs.AI
收藏

从表现到认知架构:一个可扩展框架

From Manifestations to Cognitive Architectures: a Scalable Framework

Avatar Cognition(阿凡达认知公司);Universitat Politècnica de Catalunya - BarcelonaTech(加泰罗尼亚理工大学 - 巴塞罗那技术学院)

Alfredo Ibias, Guillem Ramirez-Miranda, Enric Guinovart, Eduard Alarcon

AI总结:

本文提出一个可扩展计算框架,将现实视为信息源,从空间分布式表示原语出发构建长期记忆和工作记忆等经典认知架构要素,以推动通用人工智能建模方法发展。

摘要:

人工智能领域充斥着优化方法。在本文中,我们将重点转向开发建模方法,以使我们更接近通用人工智能。为此,我们提出一种新颖的方式,将现实解释为信息源,随后将其转化为一个能够捕获并表征此类信息的计算框架。该框架能够从仅处理空间分布式表示的简单原语出发,构建经典认知架构的要素,如长期记忆和工作记忆。此外,它以无缝可扩展的层次化方式实现了这种垂直性水平。

英文摘要:

The Artificial Intelligence field is flooded with optimisation methods. In this paper, we change the focus to developing modelling methods with the aim of getting us closer to Artificial General Intelligence. To do so, we propose a novel way to interpret reality as an information source, that is later translated into a computational framework able to capture and represent such information. This framework is able to build elements of classical cognitive architectures, like Long Term Memory and Working Memory, starting from a simple primitive that only processes Spatial Distributed Representations. Moreover, it achieves such level of verticality in a seamless scalable hierarchical 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。

↑