Inducing Relational Concepts with Neural Networks via the LINUS System

This paper presents a method to induce relational concepts with neural networks using the inductive logic programming system LINUS. Some first-order inductive learning tasks taken from machine learning literature were applied successfully, thus confirming the quality of the hypothesis generated by neural networks.

• Type: Conference
• Year: 1998
• Where: ICONIP
• Authors: Rodrigo Basilio, Gerson Zaverucha, Artur S. d'Avila Garcez
• Keywords: First-order Inductive Learning, ICONIP 1998, ICONIP 2007, Inductive Logic Programming, Neural Networks