Guiding Backprop by Inserting Rules

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.

Authors

• Sebastian Bader 0001
• Steffen Hölldobler
• Nuno C. Marques

Keywords

No keywords are indexed for this paper.