A Practical Guide to Support Vector Classication

By Chih-Wei Hsu, Chih-Jen Lin. 2008

7,108 citations recorded by the source corpus.

Subfields: Optimization & Training, Statistical Learning Theory

How researchers see this paper

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

In Optimization & Training

In Statistical Learning Theory

Citations in the corpus

AutoML: A Survey of the State-of-the-Art (2019, methodology): “To exploit well-performing region of hyperparameter space, Hsu et al. [97] recommend using a coarse grid ﬁrst, and after ﬁnding a better region on the gird, they implement a ﬁner grid search on that region.”
Stealing Hyperparameters in Machine Learning (2018, methodology): “The crossentropy loss function is adopted by logistic regression [20], while square and regular hinge loss functions are adopted by support vector machine and its variants [21].”
Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “This drawback is partially eliminated by contracting grid search (Hsu et al., 2003; Hesterman et al., 2010).”
Knowledge Matters: Importance of Prior Information for Optimization (2013, background): “For the polynomial kernel, γ controls the flexibility of the classifier (degree of the polynomial) as the number of parameters increases (Hsu et al., 2003; Ben-Hur and Weston, 2010).”
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning (2017, methodology): “Note that the problem of finding the best settings for the parameter β of the Gaussian kernel is a well known problem (Hsu et al., 2003).”
Real-Time Detection of Driver Cognitive Distraction Using Support Vector Machines (2007, methodology): “When data are not linearly separable in the feature space, the positive penalty parameter C [ 26 ] allows for training error e by specifying the cost of misclassified training instances.”
A data mining approach to predict forest fires using meteorological data (2007, methodology): “In particular, the RMiner uses the ran-domForest (RF algorithm by L. Breiman and A. Cutler), nnet (for the NN) and and kernlab (LIBSVM tool [13]) packages.”
Hierarchical Coding Vectors for Scene Level Land-Use Classification (2016, background): “…(HA) [12], Soft Assignment (SA) [6], Local Coordinate Coding (LCC) [13], Locality-constrained Linear Coding (LLC) [14], Vector of Locally Aggregated Descriptors (VLAD) [15], FV [7]), and (3) more complex classiﬁers (e.g., Support Vector Machine (SVM) [16], Extreme Learning Machine (ELM) [17]).”
Nontechnical Loss Detection for Metered Customers in Power Utility Using Support Vector Machines (2010, background): “The parameter defined as in the decision function in (8) [44], was computed to be 0.”
Combining SVMs with Various Feature Selection Strategies (2006, methodology): “[17] recommends using the RBF kernel in the SVM.”
A comparative study on ApEn, SampEn and their fuzzy counterparts in a multiscale framework for feature extraction (2010, background): “Among them, RBF kernel is preferred because of fewer hyper-parameters and fewer numerical difficulties ( Hsu et al., 2009 ).”
Co-occurrence Histograms of Oriented Gradients for Pedestrian Detection (2009, methodology): “SVM learning problems much faster than previous solvers such as LIBSVM [18] and SVMLight [19].”