Information Technology Reference
In-Depth Information
A Framework for Machine Learning with
Ambiguous Objects
Zhi-Hua Zhou
National Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210093, China
zhouzh@nju.edu.cn
Machine learning tries to improve the performance of the system automatically
by learning from experiences, e.g., objects or events given to the system as
training samples. Generally, each object is represented by an instance (or feature
vector) and is associated with a class label indicating the semantic meaning of
that object. For ambiguous objects which have multiple semantic meanings,
traditional machine learning frameworks may be less powerful. This talk will
introduce a new framework for machine learning with ambiguous objects.
