Rule extraction from support vector machines
By Haydemar Núñez, Cecilio Angulo, Andreu Català. 2002
97 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.
- Nahla H. Barakat
- Riccardo Guidotti
- Emilio Carrizosa
- Dino Pedreschi
- Salvatore Ruggieri
- Andrew P. Bradley
- Fosca Giannotti
- David Martens
Citations in the corpus
- Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “Classification rules have been widely used to explain neural networks [2, 3, 21] but also to understand the global behavior of SVMs [15, 27].”
- A Survey of Methods for Explaining Black Box Models (2018, methodology): “ques fdirectly extract rules which relate the inputs and outputs of the predictor (e.g. [20,37]), while decompositional approaches are closely intertwined with the internal structure of the SVM (e.g. [70,28]). We recall that, in Table 1 we identify with the term generalizable the pedagogical approac”
- Comprehensible credit scoring models using rule extraction from support vector machines (2007, neutral): “Workings of SVM+Prototype [21].”
- Rule Extraction from Support Vector Machines: A Sequential Covering Approach (2007, methodology): “Three types of rejoins are formed: ellipsoids [3], hyperrectangles [3], [4], [5], and hypercubes [1].”
- Fuzzy rule extraction from support vector machines (2005, methodology): “In [ 14 ], the method SVM+Prototype obtains the support vectors for each class.”
- 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 ].”
- Extracting the knowledge embedded in support vector machines (2004, methodology): “Four other rule sets obtained in [I ][ 20 ][17][ 121 could be checked in corresponding papers.”
- Rule Extraction from Trained Support Vector Machines (2005, methodology): “The prediction error of HRE on iris data set is 0.033, which is smaller than that of ellipse (0.040) and interval (0.040) rules reported in [ 5 ].”