Complexity and intelligence
Giorgio Parisi

TL;DR
This paper explores the properties of Algorithmic Complexity and logical depth, applying these concepts to understand machine learning and proposing a measure of machine intelligence based on its propensity to learn rules.
Contribution
It introduces the concept of machine propensity to learn rules and defines machine intelligence using properties of Algorithmic Complexity and logical depth.
Findings
Properties of Algorithmic Complexity and logical depth are relevant to learning.
A new measure of machine intelligence based on rule learning propensity.
Discussion of the relationship between complexity, logical depth, and machine learning.
Abstract
In this paper I will discuss the properties of the Algorithmic Complexity, presenting the most relevant properties. The related concept of logical depth is also introduced. These properties will be used to study the problem of learning from example, paying a special attention to machine learning. We introduce the propensity of a machine to learn a rule and we use it define the intelligence of a machine.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms
