... multi-class classification 多元分类 weight decay 权重衰减 self-taught learning 自我学习/自学习 ...
基于6个网页-相关网页
为抑制计算机层析造影（CT）系统重建图像中出现的金属伪影，提高图像的质量，采用一种基于金属投影非线性权重衰减的方法进行校正。
A metal artifacts reduction method using nonlinear weights was developed to suppress metal artifacts in X-ray CT(computerized tomography) images to improve the image quality.
而这三个最基础的权重因素就是亲密度、权重、时间衰减。
The three original EdgeRank elements - Affinity, Weight and Time Decay - are still factors in News Feed ranking, but "other things are equally important," he says.
应用推荐