Unstructured pruning is well suited to reduce the memory footprint of convolutional neural
networks (CNNs), both at training and inference time. CNNs contain parameters arranged in …

State-of-the-art deep learning models have a parameter count that reaches into the billions.
Training, storing and transferring such models is energy and time consuming, thus costly. A …

Neural network pruning reduces network complexity and storage by removing unimportant
connections in the network, enabling network miniaturization, fast training and inference …

One-shot Network Pruning at Initialization (OPaI) is an effective method to decrease network
pruning costs. Recently, there is a growing belief that data is unnecessary in OPaI. However …

We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel
approach that enhances the computational efficiency of CNNs by selectively processing …

With the continuous improvement of network accuracy, the depth and width of the network
also increase, so the requirements for storage and operation equipment are also higher and …

With the continuous increase of the number of network layers, while the network
performance is constantly improving, the complexity of the network is also increasing …