Extracting Propositional Rules from Feed-forward Neural Networks - A New Decompositional Approach

In this paper, we present a new decompositional approach for the extraction of propositional rules from feed-forward neural networks of binary threshold units. After decomposing the network into single units, we show how to extract rules describing a unit’s behavior. This is done using a suitable search tree which allows the pruning of the search space. Furthermore, we present some experimental results, showing a good average runtime behavior of the approach.

• Type: Conference
• Year: 2007
• Where: IJCAI
• Authors: Sebastian Bader, Steffen Hölldobler, Valentin Mayer-Eichberger
• Keywords: Artificial Intelligence, Average Runtime Behavior, Binary Threshold Units, Feed-forward Neural Networks, IJCAI 2007