Sparse tensors are rapidly becoming critical components of modern deep
l...
Image resolution has a significant effect on the accuracy and computatio...
ML workloads are becoming increasingly popular in the cloud. Good cloud
...
Tensor kernels in machine learning (ML) often correspond to pure mathema...
Graph neural networks (GNNs), an emerging deep learning model class, can...
We present a new video storage system (VSS) designed to decouple high-le...
Quantization is a key technique to reduce the resource requirement and
i...
Cost-efficiency and training time are primary concerns in cloud-based
di...
A core problem in hardware-software codesign is in the sheer size of the...
Compressed videos constitute 70
rates far outpace compute and storage im...
State of the art deep learning models have made steady progress in the f...
Consumer genetic testing has become immensely popular in recent years an...
Hardware acceleration is an enabler for ubiquitous and efficient deep
le...
We introduce a learning-based framework to optimize tensor programs for ...
Distributed deep neural network (DDNN) training constitutes an increasin...
Stochastic computing (SC) is an emerging computing technique that promis...
There is an increasing need to bring machine learning to a wide diversit...
Scalable frameworks, such as TensorFlow, MXNet, Caffe, and PyTorch drive...
Most work in the deep learning systems community has focused on faster
i...
- The primary author has withdrawn this paper due to conflict of interes...
Cameras are the defacto sensor. The growing demand for real-time and
low...
Recent advances in neural networks (NNs) exhibit unprecedented success a...
Application trends, device technologies and the architecture of systems ...
Similarity search is a key to a variety of applications including
conten...