Add to ORKGThis work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the most effective implementations of deep learning (DL) algorithms for GPUs. GPUs are the most commonly used accelerators for deep learning computations. One of the most common techniques for improving the efficiency of CNN models is weight pruning and quantization. There are two main types of pruning: structural and non-structural. The first enables much easier acceleration on many type of accelerators, but with this type it is difficult to achieve a sparsity level and accuracy as high as that obtained with th...
As recent neural networks are being improved to be more accurate, their model's size is exponentiall...
Neural networks get more difficult and longer time to train if the depth become deeper. As deep neur...
In recent years, deep neural networks have achieved remarkable results in various artificial intelli...
In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage ...
Convolutional neural network (CNN) is an important deep learning method. The convolution operation t...
This thesis presents a few methods to accelerate the inference of Deep Neural Networks that are lar...
Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed...
Deep neural network models are commonly used in various real-life applications due to their high pre...
In recent years, deep learning models have become popular in the real-time embedded application, but...
We present a library that provides optimized implementations for deep learning primitives. Deep lear...
Convolutional deep neural networks (CNNs) has been shown to perform well in difficult learning tasks...
Deep learning is a branch of machine learning that aims to extract multiple simple features from da...
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are...
DNNs have been finding a growing number of applications including image classification, speech recog...
Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services...
As recent neural networks are being improved to be more accurate, their model's size is exponentiall...
Neural networks get more difficult and longer time to train if the depth become deeper. As deep neur...
In recent years, deep neural networks have achieved remarkable results in various artificial intelli...
In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage ...
Convolutional neural network (CNN) is an important deep learning method. The convolution operation t...
This thesis presents a few methods to accelerate the inference of Deep Neural Networks that are lar...
Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed...
Deep neural network models are commonly used in various real-life applications due to their high pre...
In recent years, deep learning models have become popular in the real-time embedded application, but...
We present a library that provides optimized implementations for deep learning primitives. Deep lear...
Convolutional deep neural networks (CNNs) has been shown to perform well in difficult learning tasks...
Deep learning is a branch of machine learning that aims to extract multiple simple features from da...
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are...
DNNs have been finding a growing number of applications including image classification, speech recog...
Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services...
As recent neural networks are being improved to be more accurate, their model's size is exponentiall...
Neural networks get more difficult and longer time to train if the depth become deeper. As deep neur...
In recent years, deep neural networks have achieved remarkable results in various artificial intelli...