TY - JOUR
T1 - EasySVM
T2 - A visual analysis approach for open-box support vector machines
AU - Ma, Yuxin
AU - Chen, Wei
AU - Ma, Xiaohong
AU - Xu, Jiayi
AU - Huang, Xinxin
AU - Maciejewski, Ross
AU - Tung, Anthony K.H.
N1 - Funding Information:
This work was supported in part by the National Basic Research Program of China (973 Program, No. 2015CB352503), the Major Program of National Natural Science Foundation of China (No. 61232012), and the National Natural Science Foundation of China (No. 61422211).
Publisher Copyright:
© 2017, The Author(s).
PY - 2017/6/1
Y1 - 2017/6/1
N2 - 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 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.
AB - 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 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.
KW - high-dimensional visualization
KW - rule extraction
KW - support vector machines (SVMs)
KW - visual analysis
KW - visual classification
UR - http://www.scopus.com/inward/record.url?scp=85046766170&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046766170&partnerID=8YFLogxK
U2 - 10.1007/s41095-017-0077-5
DO - 10.1007/s41095-017-0077-5
M3 - Article
AN - SCOPUS:85046766170
SN - 2096-0433
VL - 3
SP - 161
EP - 175
JO - Computational Visual Media
JF - Computational Visual Media
IS - 2
ER -