Dense matrix multiply (MM) serves as one of the most heavily used kernels in deep learning
applications. To cope with the high computation demands of these applications …

Live video accounts for a significant volume of today's Internet video. Despite a large
number of efforts to enhance user quality of experience (QoE) both at the ingest and …

Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A
backdoor is often embedded in the target DNNs through injecting a backdoor trigger into …

As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy
and solve more complex problems. This trend has been enabled by an increase in available …

Serialization frameworks are a fundamental component of scale-out systems, but introduce
significant compute overheads. However, they are amenable to acceleration with …

Quantization is a popular way of increasing the speed and lowering the memory usage of
Convolution Neural Networks (CNNs). When labelled training data is available, network …

With the increase in the computation intensity of the chip, the mismatch between
computation layer shapes and the available computation resource significantly limits the …

The massive growth of machine learning-based applications and the end of Moore's law
have created a pressing need to redesign computing platforms. We propose Lightning, the …

Emerging deep learning-based video analytics tasks demand computation-intensive neural
networks and powerful computing resources on the cloud to achieve high accuracy. Due to …

Recent advances in machine learning (ML) have produced KiloByte-size models that can
directly run on constrained IoT devices. This approach avoids expensive communication …