Search Results

Quantum Neural Networks (QNNs) are one of the most promising applications that can be implemented on NISQ-era quantum computers. In this study, we observe that QNNs often suffer from gate redundancy, which hugely declines the performance and accuracy of ...

Neural Architecture Search (NAS) is a fast-developing research field to promote automatic machine learning. Among the recently popular NAS methods, one-shot NAS has attracted significant attention since it greatly reduces the training cost ...

In the current noisy intermediate-scale quantum (NISQ) Era, Quantum Computing faces significant challenges due to noise, which severely restricts the application of computing complex algorithms. Superconducting quantum chips, one of the pioneer quantum ...

Ensuring the reliability of deep neural networks (DNNs) is paramount in safety-critical applications. Although introducing supplementary fault-tolerant mechanisms can augment the reliability of DNNs, an efficiency tradeoff may be introduced. This study ...

To efficiently process a large amount of deep neural network models can be challenging, due to significant differences among models and even layers. Nowadays, systolic array has become a common architecture for processing neural networks. With ...

• We introduce well validated systolic array performance and energy models.
• We propose a scheduling strategy for heterogeneous systolic array accelerators.
• We propose a task decomposition algorithm for CNN tasks.

The use of indwelling closed thoracic drainage tubes in the wedge resection of the lungs is of great significance to postoperative recovery. However, there are potential risks.

To explore the design feasibility and application ...

The emergence of Neural Architecture Search (NAS) enables an automated neural network development process that potentially replaces manually-enabled machine learning expertise. A state-of-the-art NAS method, namely One-Shot NAS, has been proposed to ...

As convolutional neural network CNN accelerators are being adopted in emerging safety-critical areas, their reliability becomes prominent. The systolic array is widely used as the major processing structure in CNN accelerators, so its reliability ...

• We propose the first microarchitecture level fault injection framework saca-FI to evaluate the resiliency characteristics of CNN accelerator’s systolic array.
• We comprehensively analyze the resiliency of three commonly used CNN models.

The convolutional neural network (CNN) is an important deep learning method, which is widely used in many fields. However, it is very time consuming to implement the CNN where convolution usually takes most of the time. There are many zero values in ...

As one of the most complex parts in manufacturing systems, scheduling plays an important role in the efficient allocation of resources to meet individual customization requirements. However, due to the uncertain disruptions (e.g., task arrival time, ...

Convolutional neural networks (CNNs) have been widely adopted in many deep learning applications. However, training a deep CNN requests intensive data transfer, which is both time and energy consuming. Using resistive random-access memory (ReRAM) to ...

Energy efficiency is essential for federated learning (FL) over mobile devices and its potential prosperous applications. Different from existing communication efficient FL research efforts, which regard communication energy consumption as the bottleneck,...

The Clock Constraint Specification Language (CCSL) has been widely acknowledged as a promising system-level specification for the modeling and analysis of timing behaviors of real-time and embedded systems. However, along with the increasing complexity of ...

Encryption of streaming video is becoming critical to the success of commercial enterprise and to consumers alike. To meet copyright and privacy requirements, encrypting video data on-the-fly during transmission is necessary. In this ...

Federated learning (FL) has been recognized as a promising collaborative on-device machine learning method in the design of Internet of Things (IoT) systems. However, most existing FL methods fail to deal with IoT applications that contain a variety of ...

The core of recommendation systems is to explore users’ preferences from users’ historical records and accordingly recommend items to meet users’ interests. Previous works explore interaction graph to capture multi-order collaborative signals and ...

Dynamic graph traversals (DGTs) currently are widely used in many important application domains, especially in this big-data era that urgently demands high-performance graph processing and analysis. Unlike static graph traversals, DGTs in real-world ...

Behaviorally similar neighbors in the interaction graph have been actively explored to facilitate the collaboration between users and items and address the interaction sparsity issue. We investigate homogenous neighbors between users ...

The ocean has been an important research site for scientists in recent years. Many marine creatures with soft bodies such as sea cucumbers are fragile and easily deformed, so it is difficult when grasping these kinds of targets. In this regard, ...

A method is proposed for adaptive fundus image enhancement so as to restore the color images that are with extremely low or nonuniform brightness. Our proposed method is capable of increasing the brightness, contrast of images without losing original ...