摘要
In this paper we have pointed out an important source of inefficiency in SMO algorithm that is caused bythe operation with a single threshod value. We have suggested modifications of SMO algorithm that overcome theproblem by efficiently maintaining and updating two threshold parameters. Our experiments show that these modifi-cations speed up the SMO algorithm.
In this paper we have pointed out an important source of inefficiency in SMO algorithm that is caused by the operation with a single threshod value. We have suggested modifications of SMO algorithm that overcome the problem by efficiently maintaining and updating two threshold parameters. Our experiments show that these modifications speed up the SMO algorithm.
出处
《计算机科学》
CSCD
北大核心
2003年第8期128-129,133,共3页
Computer Science
