Related papers: Diffractive Magic Cube Network with Super-high Cap…

Future wireless networks will be characterized by heterogeneous traffic requirements. Such requirements can be low-latency or minimum-throughput. Therefore, the network has to adjust to different needs. Usually, users with low-latency…

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the…

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning…

The Deep Material Network (DMN) has emerged as a powerful framework for multiscale materials modeling, enabling efficient and accurate prediction of material behavior across different length scales. Unlike conventional data-driven…

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based…

Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This…

We consider the problem of designing a diffractive neural network (DNN) consisting of a set of sequentially placed phase diffractive optical elements (DOEs) and intended for the optical solution of several given classification problems at…

In this study, we propose a novel data-driven reduced-order model for complex dynamics, including nonlinear, multi-attractor, multi-frequency, and multiscale behaviours. The starting point is a fully automatable cluster-based network model…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

This paper applies the recent fast iterative neural network framework, Momentum-Net, using appropriate models to low-dose X-ray computed tomography (LDCT) image reconstruction. At each layer of the proposed Momentum-Net, the model-based…

Accurate medical image segmentation requires effective modeling of both long-range dependencies and fine-grained boundary details. While transformers mitigate the issue of insufficient semantic information arising from the limited receptive…

Neural networks provide a powerful tool for applications from classification and regression to general purpose alternative computing. Photonics have the potential to provide enormous speed benefits over electronic and software networks,…

Dense optical flow estimation is challenging when there are large displacements in a scene with heterogeneous motion dynamics, occlusion, and scene homogeneity. Traditional approaches to handle these challenges include hierarchical and…

Deep neural network (DNN) has emerged as the most important and popular artificial intelligent (AI) technique. The growth of model size poses a key energy efficiency challenge for the underlying computing platform. Thus, model compression…

It is difficult for free space optical communication to be applied in mobile communication due to the obstruction of obstacles in the environment, which is expected to be solved by reconfigurable intelligent surface technology. The…

Network reconfiguration can significantly increase the hosting capacity (HC) for distributed generation (DG) in radially operated systems, thereby reducing the need for costly infrastructure upgrades. However, when the objective is DG…

While the deployment of deep learning models on edge devices is increasing, these models often lack robustness when faced with dynamic changes in sensed data. This can be attributed to sensor drift, or variations in the data compared to…

With the development of deep neural network (DNN) enabled applications, achieving high hardware resource efficiency on diverse workloads is non-trivial in heterogeneous computing platforms. Prior works discuss dedicated architectures to…