Rule Extraction from Support Vector Machines

By Joachim Diederich. 2008

222 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “Rule based learners are clearly transparent models that have been often used to explain complex models by generating rules that explain their predictions [126,127,190,191] .”
Binarized Support Vector Machines (2010, methodology): “Binarizing continuous predictor variables has also been proposed in the socalled rule extraction procedures within SVM (Barakat and Diederich 2004, 2005; Fung et al. 2005; Martens et al. 2007; Núñez et al. 2002) and neural networks (Andrews et al.”
Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME (2018, methodology): “SVM+Prototypes [11] is a decompositional rule extraction algorithm that makes use of KMeans clustering to extract rules from SVM classifiers by focusing on support vectors.”
Rule extraction from support vector machines: A review (2010, methodology): “4, the algorithm [25,28] utilizes the SVM SVs, training data and the separating hyper-plane to define regions (ellipsoids and hyper-rectangles), which are then refined and translated into rules.”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, methodology): “Similarly, exploiting the intuitiveness of rules, Rule Extraction was developed to interpret artificial neural networks (ANN) and support vector machines (SVM), with work spanning from the 1990s to 2000s (e.g., [6, 139]).”
Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning (2017, background): “More recently, Diederich et al. published a book on techniques to extract symbolic rules from Support Vector Machines (SVMs) [10].”
Rule Extraction from Support Vector Machines: A Sequential Covering Approach (2007, methodology): “Therefore, several methods have been introduced for rule extraction from both ANNs [2] and, more recently, SVMs [1], [3], [4], [5], [6], [7], [8], which will be summarized in Section 4.”
A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue (2007, methodology): “propose a ‘‘SVM + prototypes’’ method in which support vectors and the prototype points defined by the K-means clustering algorithm are used to determine the rules [41].”
Rule-Based Learning Systems for Support Vector Machines (2006, methodology): “Thus, a rule extraction procedure can be derived – as a dual one from the formerly presented one [18] – : first a standard SVM is learned on the training set for the supervised classification problem, generating a set of of support vectors, next a clustering algorithm determines prototype vectors fo”
Rule Extraction from Support Vector Machines: An Overview of Issues and Application in Credit Scoring (2008, methodology): “One of the few rule extraction methods designed speciﬁcally for support vector machines is the SVM+Prototypes method proposed in [46].”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “SVM+Prototypes [299] is based on a clustering algorithm to detect the prototype vectors for each class, after the decision”