首页>
外国专利>
USING META-LEARNING FOR AUTOMATIC GRADIENT-BASED HYPERPARAMETER OPTIMIZATION FOR MACHINE LEARNING AND DEEP LEARNING MODELS
USING META-LEARNING FOR AUTOMATIC GRADIENT-BASED HYPERPARAMETER OPTIMIZATION FOR MACHINE LEARNING AND DEEP LEARNING MODELS
展开▼
机译:将元学习用于基于机器学习和深度学习模型的基于梯度的自动超优化
展开▼
页面导航
摘要
著录项
相似文献
摘要
Techniques are provided herein for optimal initialization of value ranges of machine learning algorithm hyperparameters and other predictions based on dataset meta-features. In an embodiment for each particular hyperparameter of a machine learning algorithm, a computer invokes, based on an inference dataset, a distinct trained metamodel for the particular hyperparameter to detect an improved subrange of possible values for the particular hyperparameter. The machine learning algorithm is configured based on the improved subranges of possible values for the hyperparameters. The machine learning algorithm is invoked to obtain a result. In an embodiment, a gradient-based search space reduction (GSSR) finds an optimal value within the improved subrange of values for the particular hyperparameter. In an embodiment, the metamodel is trained based on performance data from exploratory sampling of configuration hyperspace, such as by GSSR. In various embodiments, other values are optimized or intelligently predicted based on additional trainable metamodels.
展开▼