首页>
外国专利>
SELECTING HYPER PARAMETERS FOR MACHINE LEARNING ALGORITHMS BASED ON PAST TRAINING RESULTS
SELECTING HYPER PARAMETERS FOR MACHINE LEARNING ALGORITHMS BASED ON PAST TRAINING RESULTS
展开▼
机译:基于过去训练结果的机器学习算法超级参数选择
展开▼
页面导航
摘要
著录项
相似文献
摘要
Systems and methods for selecting hyper parameters for machine learning algorithms based on past training results are provided. For example, groups of values of hyper parameters may be obtained. Further, in some examples, results of training the machine learning algorithm using different pluralities of training examples and/or the different group of values of hyper parameters may be obtained. Further, in some examples, the results and the groups of values of hyper parameters may be used to select at least one value of a hyper parameter for a prospective training of the machine learning algorithm.
展开▼