首页>
外国专利>
DITHERED QUANTIZATION OF PARAMETERS DURING TRAINING WITH A MACHINE LEARNING TOOL
DITHERED QUANTIZATION OF PARAMETERS DURING TRAINING WITH A MACHINE LEARNING TOOL
展开▼
机译:用机器学习工具训练过程的抖动量化
展开▼
页面导航
摘要
著录项
相似文献
摘要
A machine learning tool uses dithered quantization of parameters during training of a machine learning model such as a neural network. The machine learning tool receives training data and initializes certain parameters of the machine learning model (e.g, weights for connections between nodes of a neural network, biases for nodes). The machine learning tool trains the parameters in one or more iterations based on the training data. In particular, in a given iteration, the machine learning tool applies the machine learning model to at least some of the training data and, based at least in part on the results, determines parameter updates to the parameters. The machine learning tool updates the parameters using the parameter updates and a dithered quantizer function, which can add random values before a rounding or truncation operation.
展开▼