Guiding backprop by inserting rules

Sebastian Bader, Steffen Hölldobler, Nuno C. Marques

Research output: Contribution to journalConference articlepeer-review

8 Citations (Scopus)

Abstract

We report on an experiment where we inserted symbolic rules into a neural network during the training process. This was done to guide the learning and to help escape local minima. The rules are constructed by analysing the errors made by the network after training. This process can be repeated, which allows to improve the network performance again and again. We propose a general framework and provide a proof of concept of the usefullness of our approach.

Original languageEnglish
Pages (from-to)19-22
Number of pages4
JournalCEUR Workshop Proceedings
Volume366
Publication statusPublished - 1 Dec 2008
Event4th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2008 - Patras, Greece
Duration: 21 Jul 200821 Jul 2008

Fingerprint

Dive into the research topics of 'Guiding backprop by inserting rules'. Together they form a unique fingerprint.

Cite this