© 2019 IEEE. Training deep convolutional neural networks such as VGG and ResNet by gradient descent is an expensive exercise requiring specialized hardware such as GPUs. Recent works have examined the possibility of approximating the gradient computation while maintaining the same convergence properties. While promising, the approximations only work on relatively small datasets such as MNIST. They also fail to achieve real wall-clock speedups due to lack of efficient GPU implementations of the proposed approximation methods. In this work, we explore three alternative methods to approximate gradients, with an efficient GPU kernel implementation for one of them. We achieve wall-clock speedup with ResNet-20 and VGG-19 on the CIFAR-10 dataset u...
This paper proposes an algorithmic optimization for the feature extractors of biologically inspired ...
Recent years saw an increasing success in the application of deep learning methods across various do...
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving their...
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs)...
Deep learning has achieved great performance in various areas, such as computer vision, natural lang...
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...
In stochastic gradient descent (SGD) and its variants, the optimized gradient estimators may be as e...
We describe the neural-network training framework used in the Kaldi speech recogni-tion toolkit, whi...
Deep neural networks currently play a prominent role in solving problems across a wide variety of di...
The ability to train large-scale neural networks has resulted in state-of-the-art per-formance in ma...
Open-source deep learning tools has been distributed numerously and has gain popularity in the past ...
The convolutional neural networks (CNNs) have proven to be powerful classification tools in tasks th...
Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed...
The convolution neural network (CNN) has achieved state-of-the-art performance in many computer visi...
This paper proposes an algorithmic optimization for the feature extractors of biologically inspired ...
Recent years saw an increasing success in the application of deep learning methods across various do...
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving their...
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs)...
Deep learning has achieved great performance in various areas, such as computer vision, natural lang...
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...
In stochastic gradient descent (SGD) and its variants, the optimized gradient estimators may be as e...
We describe the neural-network training framework used in the Kaldi speech recogni-tion toolkit, whi...
Deep neural networks currently play a prominent role in solving problems across a wide variety of di...
The ability to train large-scale neural networks has resulted in state-of-the-art per-formance in ma...
Open-source deep learning tools has been distributed numerously and has gain popularity in the past ...
The convolutional neural networks (CNNs) have proven to be powerful classification tools in tasks th...
Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed...
The convolution neural network (CNN) has achieved state-of-the-art performance in many computer visi...
This paper proposes an algorithmic optimization for the feature extractors of biologically inspired ...
Recent years saw an increasing success in the application of deep learning methods across various do...
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving their...