On computable abstractions (a conceptual introduction)

TL;DR

This paper introduces computable abstractions and abstractional machines that enable computers to build their own understanding, serving as foundational tools for intellectual tasks like natural language processing.

Contribution

It presents the concept of computable abstractions and defines abstractional machines capable of autonomously developing understanding based on these abstractions.

Findings

Abstractional machines can construct understanding through computable abstractions.

The approach is applicable to natural language processing tasks.

Computable abstractions serve as building blocks for machine understanding.

Abstract

This paper introduces abstractions that are meaningful for computers and that can be built and used according to computers' own criteria, i.e., computable abstractions. It is analyzed how abstractions can be seen to serve as the building blocks for the creation of one own's understanding of things, which is essential in performing intellectual tasks. Thus, abstractional machines are defined, which following a mechanical process can, based on computable abstractions, build and use their own understanding of things. Abstractional machines are illustrated through an example that outlines their application to the task of natural language processing.