Enhancing Transparency of Blackbox Softmargin SVM by Integrating Databased Prior Information
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 3 months ago.

Enhancing Transparency of Blackbox Softmargin SVM by Integrating Databased Prior Information
The lack of transparency often makes the blackbox models difficult to be applied to many practical domains. For this reason, the current work, from the blackbox model input port, proposes to incorporate databased prior information into the blackbox softmargin SVM model to enhance its transparency. The concept and incorporation mechanism of databased prior information are successively developed, based on which the transparent or partly transparent SVM optimization model is designed and then solved through handily rewriting the optimization problem as a nonlinear quadratic programming problem. An algorithm for mining databased linear prior information from data set is also proposed, which generates a linear expression with respect to two appropriate inputs identified from all inputs of system. At last, the proposed transparency strategy is applied to eight benchmark examples and two real blast furnace examples for effectiveness exhibition.
Enhancing Transparency of Blackbox Softmargin SVM by Integrating Databased Prior Information
by Shaohan Chen, Chuanhou Gao, Ping Zhang
https://arxiv.org/pdf/1710.02924v1.pdf
You must be logged in to reply to this topic.