Abstract Recently, Vision Transformer (ViT) has continuously established new milestones in
the computer vision field, while the high computation and memory cost makes its …

Channel pruning has been broadly recognized as an effective technique to reduce the
computation and memory cost of deep convolutional neural networks. However …

Observing that the existing model compression approaches only focus on reducing the
redundancies in convolutional neural networks (CNNs) along one particular dimension (eg …

Over-the-air federated learning (OTA-FL) is a distributed machine learning technique where
multiple devices collaboratively train a shared model without sharing their raw data with a …

Deep learning-based super-resolution (SR) has gained tremendous popularity in recent
years because of its high image quality performance and wide application scenarios …

Deep neural networks (DNNs) are effective in solving many real-world problems. Larger
DNN models usually exhibit better quality (eg, accuracy) but their excessive computation …

Federated Learning (FL) has achieved significant achievements recently, enabling
collaborative model training on distributed data over edge devices. Iterative gradient or …

With the yearning for deep learning democratization, there are increasing demands to
implement Transformer-based natural language processing (NLP) models on resource …

Multiple suppression is a very important step in seismic data processing. To suppress
surface-related multiples, we develop a self-supervised deep neural network method based …

Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with
advances in deep neural networks (DNNs), have opened up new opportunities for en-abling …