Rule extraction from linear support vector machines

Fung, Glenn; Sandilya, Sathyakama; Rao, R. Bharat

doi:10.1145/1081870.1081878

Cited by 111 publications

(60 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, recently, a set of methods were developed to simplify model complexity while managing non-linearity [16,17]. One representative scheme is to build multiple local models to approximate the global one [11,18,19] [20,21]. Martens et al [8] provided a comprehensive study of rule extraction from SVMs.…”

Section: Support Vector Machinesmentioning

confidence: 99%

EasySVM: A visual analysis approach for open-box support vector machines

Chen

et al. 2017

Comp. Visual Media

View full text Add to dashboard Cite

Support vector machines (SVMs) are supervised learning models traditionally employed for classification and regression analysis. In classification analysis, a set of training data is chosen, and each instance in the training data is assigned a categorical class. An SVM then constructs a model based on a separating plane that maximizes the margin between different classes. Despite being one of the most popular classification models because of its strong performance empirically, understanding the knowledge captured in an SVM remains difficult. SVMs are typically applied in a black-box manner where the details of parameter tuning, training, and even the final constructed model are hidden from the users. This is natural since these details are often complex and difficult to understand without proper visualization tools. However, such an approach often brings about various problems including trial-and-error tuning and suspicious users who are forced to trust these models blindly.The contribution of this paper is a visual analysis approach for building SVMs in an open-box manner. Our goal is to improve an analyst's understanding of the SVM modeling process through a suite of visualization techniques that allow users to have full interactive visual control over the entire SVM training process. Our visual exploration tools have been developed to enable intuitive parameter tuning, training data 2016-12-24; accepted: 2017-01-09 manipulation, and rule extraction as part of the SVM training process. To demonstrate the efficacy of our approach, we conduct a case study using a real-world robot control dataset.

show abstract

Section: Support Vector Machinesmentioning

confidence: 99%

EasySVM: A visual analysis approach for open-box support vector machines

Chen

et al. 2017

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

“…Quite a lot of recent work has addressed the problem of extracting explanations from classifiers. For instance, there are many approaches for extracting explanations from SVM (e.g., [4,9]). Most of these works use the SVM's "support vectors" to produce rules.…”

Section: Interpretable Modelsmentioning

confidence: 99%

Discovering Characterization Rules from Rankings

Salleb-Aouissi

Huang

Waltz

2009

2009 International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

“…Malone et al [3] have used Kohonen network for data mining and have used Kohonen feature maps to formulate rules. Fung et al [4] used Support Vector Machines (SVM) to extract rules from datasets by expressing the variable space as hyper-cubes. Ali et al [5] have shown it is possible to extract useful rules using decision tree induction by suggesting improvements to the existing C4.5 decision tree algorithm.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Extraction from Metacognitive Reading Strategies Data Using Induction Trees

Taylor¹,

Kulkarni²,

Mokhtari³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-The assessment of students' metacognitive knowledge and skills about reading is critical in determining their ability to read academic texts and do so with comprehension. In this paper, we used induction trees to extract metacognitive knowledge about reading from a reading strategies dataset obtained from a group of 1636 undergraduate college students. Using a C4.5 algorithm, we constructed decision trees, which helped us classify participants into three groups based on their metacognitive strategy awareness levels consisting of global, problem-solving and support reading strategies. We extracted rules from these decision trees, and in order to evaluate accuracy of the extracted rules, we built a fuzzy inference system (FIS) with the extracted rules as a rule base and classified the test dataset with the FIS. The extracted rules are evaluated using measures such as the overall efficiency and Kappa coefficient.

show abstract

Rule extraction from linear support vector machines

Cited by 111 publications

References 13 publications

EasySVM: A visual analysis approach for open-box support vector machines

EasySVM: A visual analysis approach for open-box support vector machines

Discovering Characterization Rules from Rankings

Knowledge Extraction from Metacognitive Reading Strategies Data Using Induction Trees

Contact Info

Product

Resources

About