PP-2007-11: A Fully Connectionist Model Generator for Covered

PP-2007-11: Bader, Sebastian and Hitzler, Pascal and Hölldobler, Steffen and Witzel, Andreas (2007) A Fully Connectionist Model Generator for Covered. [Report]

[img]
Preview
Text (Full Text)
PP-2007-11.text.pdf

Download (291kB) | Preview
[img] Text (Abstract)
PP-2007-11.abstract.txt

Download (655B)

Abstract

We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples, we embed the associated semantic operator into a feed-forward network and train the network using the examples. This results in the learning of first-order knowledge while damaged or noisy data is handled gracefully.

Item Type: Report
Report Nr: PP-2007-11
Series Name: Prepublication (PP) Series
Year: 2007
Uncontrolled Keywords: artificial intelligence; neural networks; connectionist systems; logic programming; neural-symbolic integration
Subjects: Logic
Date Deposited: 12 Oct 2016 14:36
Last Modified: 12 Oct 2016 14:36
URI: https://eprints.illc.uva.nl/id/eprint/245

Actions (login required)

View Item View Item