Using a vision-inspired keyword spotting framework, we propose an
archit...
This paper explores the possibility of using visual object detection
tec...
Deep neural networks have been shown to be vulnerable to backdoor, or tr...
Splitting network computations between the edge device and a server enab...
We propose CLEANN, the first end-to-end framework that enables online
mi...
In the contemporary big data realm, Deep Neural Networks (DNNs) are evol...
This paper introduces ASCAI, a novel adaptive sampling methodology that ...
Advancements in deep learning enable cloud servers to provide
inference-...
This paper proposes CodeX, an end-to-end framework that facilitates enco...
Deep neural networks (DNN) have demonstrated effectiveness for various
a...
Recent efforts on training light-weight binary neural networks offer
pro...
This paper proposes CuRTAIL, an end-to-end computing framework for
chara...