摘要
多示例学习是继监督学习、非监督学习、强化学习后的又一机器学习框架。将多示例学习和非监督学习结合起来,在传统非监督聚类算法K-means的基础上提出MI_K-means算法,该算法利用混合Hausdorff距离作为相似测度来实现数据聚类。实验表明,该方法能够有效揭示多示例数据集的内在结构,与K-means算法相比具有更好的聚类效果。
Multi-instance learning is a new machine learning framework following supervised learning, unsupervised learning and reinforcement learning. Multi-instance learning and unsupervised learning are combined. This paper proposes a new multi-instance clustering algorithm MI _K-means based on traditional unsupervised learning algorithm K-means. The algorithm MI_K-means adopts mixed Hausdorffdistanee as similar measure to carry out clustering. Experimental shows that MI_K-mcans can effectively reveal inherent structure of a multi-instance data set, and it can get better clustering effect than K-means algorithm.
出处
《计算机工程》
CAS
CSCD
北大核心
2009年第22期179-181,共3页
Computer Engineering
基金
山西省自然科学基金资助项目(20051035)
关键词
多示例学习
K-MEANS聚类
包间距
聚类有效性评价
multi-instance learning： K-means clustering
distance between bags
validity measure on clustering
