0


多任务学习艾滋病治疗筛选

Multi-Task Learning for HIV Therapy Screening
课程网址: http://videolectures.net/icml08_bickel_mtl/  
主讲教师: Steffen Bickel
开课单位: 马克斯普朗克研究所
开课时间: 2008-08-07
课程语种: 英语
中文简介:
我们讨论学习的分类进行了大量的任务的问题。我们推导产生相匹配的所有实施例,以任何给定的任务的目标分配的池重新采样的权重中的溶液。我们的工作是预测治疗的尝试为患者谁携带了HIV病毒与一组观察到的遗传特性的结果的动机问题。这种预测需要数百药物的可能组合,其中一些使用类似的生化机制作出。多任务的学习使我们能够甚至药物组合很少或根本没有训练样本预测,大幅提高了整体预测准确度。
课程简介: We address the problem of learning classifiers for a large number of tasks. We derive a solution that produces resampling weights which match the pool of all examples to the target distribution of any given task. Our work is motivated by the problem of predicting the outcome of a therapy attempt for a patient who carries an HIV virus with a set of observed genetic properties. Such predictions need to be made for hundreds of possible combinations of drugs, some of which use similar biochemical mechanisms. Multi-task learning enables us to make predictions even for drug combinations with few or no training examples and substantially improves the overall prediction accuracy.
关 键 词: 艾滋病; 生化机制; 药物组合
课程来源: 视频讲座网
最后编审: 2020-05-30:王勇彬(课程编辑志愿者)
阅读次数: 283