With the recent popularity of neural networks comes the need for efficient serving of
inference workloads. A neural network inference workload can be represented as a …

Deploying neural networks on edge devices and bringing them into our daily lives is
attracting more and more attention. However, its expensive computational cost makes many …

In the past few years, there has been an immense increase in the volume of collected data
worldwide. Dealing with the continuously growing amount of data requires two strategies …