CircConv: A Structured Convolution with Low Complexity
national conference on artificial intelligence, 2019.
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limit...More
PPT (Upload PPT)