Support Vector Machine (SVM) represents the state-of-the-art classification technique. However, training SVM on a large training set becomes a bottleneck. HeroSvm is a high-performance library for training SVM for classification to solve this problem. It has been implemented based on our proposed method . In order to facilitate the software portability and maintenance, an object-oriented method has been applied to design the package. Error handling is supported and HeroSvm is exception-safe. HeroSvm is written in C++. In the current version, a dynamic link library in windows or a shared library in linux is provided to train SVM on a large-scale learning problem efficiently for research purpose in PC platform. We expect that HeroSVM can facilitate the training of support vector machine and solve some real-world problems in various engineering fields.
References in zbMATH (referenced in 1 article )
Showing result 1 of 1.
- Niu, Xiao-Xiao; Suen, Ching Y.: A novel hybrid CNN-SVM classifier for recognizing handwritten digits (2012)