Computability-logic web: an alternative to deep learning
This paper proposes a new computational paradigm for general AI, potentially offering an alternative to deep learning for researchers and developers exploring different foundational models.
This paper introduces CoL-web, an extension of Computability Logic (CoL), as a computational model for web programming involving database updates. It demonstrates an implementation of an AI ATM using CoL (CL9) and argues for CoL-web's potential as a general AI alternative to deep learning.
{\em Computability logic} (CoL) is a powerful, mathematically rigorous computational model. In this paper, we show that CoL-web, a web extension to CoL, naturally supports web programming where database updates are involved. To be specific, we discuss an implementation of the AI ATM based on CoL (CL9 to be exact). More importantly, we argue that CoL-web supports a general AI and, therefore, is a good alternative to neural nets and deep learning. We also discuss how to integrate neural nets into CoL-web.