Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published May 2, 2024 | Version 1.0
Presentation Open

Learning Sets of Rules and Analytical Learning

  • 1. ROR icon University of Piraeus
  • 2. ROR icon National and Kapodistrian University of Athens

Description

At the core of Artificial Intelligence, two major pathways of knowledge extraction and representation have been the cornerstone for many decades: Deductive Learning, based on sets of "rules" from Predicate Calculus and Horn clauses that represent the domain experts' knowledge; and Inductive Learning, based on 'generalization by examples' by more or less 'black box' algorithms.
In this third lecture, the Deductive approach is explored via the notion of Explanation-Based Learning (EBL), which is prevalent in Logic Programming and Expert Systems, implemented by languages like Prolog and LISP. Similarly, the Inductive approach is explained via the notion of Analytical Learning, which is prevalent in the last few decades in Pattern Recognition and Machine Learning, more commonly manifested as Neural Networks, Genetic Algorithms, Deep Learning, etc.

Keywords: Machine Learning, Data Analytics, AI, Artificial Intelligence, lecture
Video: https://youtu.be/aNyoGAaa5LQ

Files

03-AI_Learning Rule Sets.pdf

Files (215.2 kB)

Name Size Download all
md5:67f151569ed43f6a2084e0dfe451f824
215.2 kB Preview Download