Algorithmic iteration for computational intelligence

Primiero, Giuseppe (2017) Algorithmic iteration for computational intelligence. Minds and Machines, 27 (3) . pp. 521-543. ISSN 0924-6495 [Article] (doi:10.1007/s11023-017-9423-8)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (392kB) | Preview

Abstract

Machine awareness is a disputed research topic, in some circles considered a crucial step in realising Artificial General Intelligence. Understanding what that is, under which conditions such feature could arise and how it can be controlled is still a matter of speculation. A more concrete object of theoretical analysis is algorithmic iteration for computational intelligence, intended as the theoretical and practical ability of algorithms to design other algorithms for actions aimed at solving well-specified tasks. We know this ability is already shown by current AIs, and understanding its limits is an essential step in qualifying claims about machine awareness and Super-AI. We propose a formal translation of algorithmic iteration in a fragment of modal logic, formulate principles of transparency and faithfulness across human and machine intelligence, and consider the relevance to theoretical research on (Super)-AI as well as the practical import of our results.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer Science > Foundations of Computing group
Item ID: 21262
Notes on copyright: The final publication is available at Springer via http://dx.doi.org/10.1007/s11023-017-9423-8
Depositing User: Giuseppe Primiero
Date Deposited: 10 Feb 2017 15:45
Last Modified: 14 Jun 2021 21:33
URI: https://eprints.mdx.ac.uk/id/eprint/21262

Actions (login required)

View Item View Item

Statistics

Downloads
Activity Overview
273Downloads
437Hits

Additional statistics are available via IRStats2.