Multi-instance learning (MIL) has been regarded by some international experts as a new learning framework parallel to the three traditional machine learning frameworks.
多示例学习被国际上一些专家认为是与传统的三大机器学习框架并列的一种新型学习框架。
For instance, a certain kind of basic neural network, the perceptron, is biased to learning only linear functions (functions with inputs that can be separated into classifications by drawing a line).
例如,某些基本的神经网络,它们的感知器只倾向于学习线形函数(通过划一条线可以把函数输入解析到分类系统中)。
The Meta-Metadata category groups information about the metadata instance itself (rather than the learning object that the metadata instance describes).
元-元数据(Meta-Metadata)范畴包括关于元数据实例自身的信息(而不是元数据实例所描述的学习对象)。
应用推荐