摘要
将小波分析与相关向量机结合,提出了一种新的机器学习方法——小波相关向量机.在模拟数据和典型数据集上的实验表明,与经典的相关向量机相比,小波相关向量机可以更好地逼近任意函数,训练时间更短,并且在有噪音的情况下具有更好的鲁棒性.
The Relevance vector machine (RVM) is a state-of-the-art machine learning algorithm in which the training procedure is in the framework of Bayesian. Experiments on simulated datasets and some popular benchmark datasets show that, compared with standard RVM, WRVM can approximate arbitrary functions better with fewer training time and more robustness under circumstances where data is corrupted by noise.
出处
《五邑大学学报(自然科学版)》
CAS
2008年第1期58-62,共5页
Journal of Wuyi University(Natural Science Edition)