Burkhardt, Sophie ; Brugger, Jannis ; Wagner, Nicolas ; Ahmadi, Zahra ; Kersting, Kristian ; Kramer, Stefan (2022)
Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation.
In: Frontiers in Artificial Intelligence, 4
doi: 10.3389/frai.2021.642263
Artikel, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (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.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Burkhardt, Sophie ; Brugger, Jannis ; Wagner, Nicolas ; Ahmadi, Zahra ; Kersting, Kristian ; Kramer, Stefan |
| Art des Eintrags: | Bibliographie |
| Titel: | Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Verlag: | Frontiers Media S.A. |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Frontiers in Artificial Intelligence |
| Jahrgang/Volume einer Zeitschrift: | 4 |
| Kollation: | 14 Seiten |
| DOI: | 10.3389/frai.2021.642263 |
| Zugehörige Links: | |
| Kurzbeschreibung (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. |
| Freie Schlagworte: | k-term DNF, stochastic local search, convolutional neural networks, logical rules, rule extraction, interpretability |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Künstliche Intelligenz und Maschinelles Lernen Forschungsfelder Forschungsfelder > Information and Intelligence Forschungsfelder > Information and Intelligence > Cognitive Science Zentrale Einrichtungen Zentrale Einrichtungen > hessian.AI - Hessisches Zentrum für Künstliche Intelligenz |
| Hinterlegungsdatum: | 02 Aug 2024 12:41 |
| Letzte Änderung: | 02 Aug 2024 12:41 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation. (deposited 13 Mai 2022 13:48)
- Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation. (deposited 02 Aug 2024 12:41) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum