首页>
外国专利>
OPERATION METHOD OF DEEP NEURAL NETWORK SYSTEM CONFIGURED TO OPTIMIZE NEURAL NETWORK MODEL
OPERATION METHOD OF DEEP NEURAL NETWORK SYSTEM CONFIGURED TO OPTIMIZE NEURAL NETWORK MODEL
展开▼
机译:深神经网络系统的操作方法,用于优化神经网络模型
展开▼
页面导航
摘要
著录项
相似文献
摘要
A method of operating a deep neural network system configured to optimize a neural network model according to an embodiment of the present invention includes generating importance parameters for a neural network model including model parameters, and an objective function corresponding to the neural network model based on the generated importance parameters. Generating, receiving training data, and simultaneously performing training on importance parameters and model parameters using stochastic gradient descent (SGD) based on the training data and the objective function. , And generating and storing a lightweight model based on a result of the training, wherein at least one of the importance parameters converges to 0 (zero) through training.
展开▼