Autoren:	Burkhardt, Sophie Brugger, Jannis Wagner, Nicole Ahmadi, Zahra Kersting, Kristian Kramer, Stefan
Titel:	Rule extraction from binary neural networks with convolutional rules for model validation
Online-Publikationsdatum:	16-Nov-2021
Erscheinungsdatum:	2021
Sprache des Dokuments:	Englisch
Zusammenfassung/Abstract:	Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and whose complexity depends on the size of the convolutional filter and not on the dimensionality of the input. Our approach is based on rule extraction from binary neural networks with stochastic local search. We show how to extract rules that are not necessarily short, but characteristic of the input, and easy to visualize. Our experiments show that the proposed approach is able to model the functionality of the neural network while at the same time producing interpretable logical rules. Thus, we demonstrate the potential of rule-based approaches for images which allows to combine advantages of neural networks and rule learning.
DDC-Sachgruppe:	004 Informatik 004 Data processing
Veröffentlichende Institution:	Johannes Gutenberg-Universität Mainz
Organisationseinheit:	FB 08 Physik, Mathematik u. Informatik
Veröffentlichungsort:	Mainz
ROR:	https://ror.org/023b0x485
DOI:	http://doi.org/10.25358/openscience-6523
Version:	Published version
Publikationstyp:	Zeitschriftenaufsatz
Nutzungsrechte:	CC BY
Informationen zu den Nutzungsrechten:	https://creativecommons.org/licenses/by/4.0/
Zeitschrift:	Frontiers in artificial intelligence 4
Seitenzahl oder Artikelnummer:	642263
Verlag:	Frontiers Media
Verlagsort:	Lausanne
Erscheinungsdatum:	2021
ISSN:	2624-8212
URL der Originalveröffentlichung:	https://doi.org/10.3389/frai.2021.642263
DOI der Originalveröffentlichung:	10.3389/frai.2021.642263
Enthalten in den Sammlungen:	JGU-Publikationen