首页>
外国专利>
COMPUTING DEVICE TO IMPROVE THE EFFICIENCY OF CONVOLUTION OPERATION BY ADJUSTING THE NUMBER OF CONVOLUTION FILTERS INCLUDED IN THE CONVOLUTIONAL NEURAL NETWORKS MODEL AND OPERATING METHOD THEREOF
COMPUTING DEVICE TO IMPROVE THE EFFICIENCY OF CONVOLUTION OPERATION BY ADJUSTING THE NUMBER OF CONVOLUTION FILTERS INCLUDED IN THE CONVOLUTIONAL NEURAL NETWORKS MODEL AND OPERATING METHOD THEREOF
展开▼
机译:计算装置通过调节卷积神经网络模型中包括的卷积滤波器的数量和其操作方法来提高卷积操作的效率
展开▼
页面导航
摘要
著录项
相似文献
摘要
Disclosed are a computing device and an operating method thereof for improving the efficiency of a convolution operation by adjusting the number of convolution filters included in a convolutional neural network model. The present invention relates to a computing device in which machine learning is completed and a convolutional neural network model is built, by appropriately adjusting the number of convolution filters to be used for a convolution operation among convolution filters existing in each convolution layer. It is about a technique that can reduce operation time and increase energy efficiency.
展开▼