Understanding deep learning is increasingly emergent as it penetrates more and more into
industry and science. In recent years, a research line from Fourier analysis sheds light on …

Federated Learning (FL) is a powerful technique to train a model on a server with data from
several clients in a privacy-preserving manner. FL incurs significant communication costs …

With the increasing stringent QoS constraints (eg, latency, bandwidth, jitter) imposed by
novel applications (eg, e-Health, autonomous vehicles, smart cities, etc.), as well as the …

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art
binary neural networks (BNN). However, the BN layer is costly to calculate and is typically …

Neural network quantization is a promising compression technique to reduce memory
footprint and save energy consumption, potentially leading to real-time inference. However …

This work is an introduction and a survey for the Special Issue on Machine Intelligence at the
Edge. The authors argue that workloads that were formerly performed in the cloud are …

Low-precision deep neural network (DNN) training has gained tremendous attention as
reducing precision is one of the most effective knobs for boosting DNNs' training time/energy …

Vision transformers have recently demonstrated great success in various computer vision
tasks, motivating a tremendously increased interest in their deployment into many real-world …

The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of
Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices …

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely
large training cost. Existing methods have attempted to accelerate the training of ViTs yet …