Search Results

Human faces have been widely adopted in many applications and systems requiring a high-security standard. Although face authentication is deemed to be mature nowadays, many existing works have demonstrated not only the privacy leakage of facial ...

There are fewer simulation studies that comprehensively consider the impact of collision events due to heterogeneous driving behaviour on multi-lane traffic flow. This comprehensive study utilized multi-agent modeling to simulate the driver-...

Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN’s overfitting properties to perform video resolution ...$$$$

Dynamic Sparse Training (DST) has been effectively addressing the substantial training resource requirements of increasingly large Deep Neural Networks (DNNs). Characterized by its dynamic "train-prune-grow" schedule during training, DST implicitly ...

First-come first-serve scheduling can result in substantial (up to 10%) of transiently idle nodes on supercomputers. Recognizing that such unfilled nodes are well-suited for deep neural network (DNN) training, due to the flexible nature of DNN training ...

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can train deep ...

The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method called the winning ticket, such that it can be trained from scratch to almost as good as ...

Aiming at the problem of contact force control of objects with different dynamic characteristics in the process of hand-object interaction of dexterous hands, this paper proposes a contact force control algorithm of dexterous hands based on ...

The human hand’s fingers are capable of precise manipulation due to the abundance of neural receptors in them. These receptors provide interactive feedback to the brain in real-time. However, complex sensors are difficult to integrate into the ...

A self-designed AMR detector named Smart Road Stud (SRS) is proposed. SRS, installed along lane markings, is not only a detector but also a lane markings enhancement device. Because a single SRS needs to detect vehicles on two lanes, the vehicle detection ...

Cloud object storage such as AWS S3 is cost-effective and highly elastic but relatively slow, while high-performance cloud storage such as AWS ElastiCache is expensive and provides limited elasticity. We present a new cloud storage service called ...

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the ...

Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Considering the computation ...

Stochastic rounding is a critical technique used in low-precision deep neural networks (DNNs) training to ensure good model accuracy. However, it requires a large number of random numbers generated on the fly. This is not a trivial task on the ...

Passenger-paid seat selection is one of the important sources of ancillary revenue for airlines, and machine learning-based willingness-to-pay identification is of great practicality for airlines to accurately tap potential willing passengers. However,...

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices, because even the powerful modern mobile devices are considered as “resource-constrained” when executing large-scale DNNs. It ...

This paper describes an impedance control strategy based on model reference adaptation in unstructured environment, aimed at the uncertainty of the environmental stiffness and the unknown of the dynamic change of the environmental position during ...

Stochastic rounding is crucial in the training of low-bit deep neural networks (DNNs) to achieve high accuracy. Unfortunately, prior studies require a large number of high-precision stochastic rounding units (SRUs) to guarantee the low-bit DNN accuracy, ...

The widespread popularity of deep neural networks (DNNs) has made it an important workload in modern datacenters. Training DNNs is both computation-intensive and memory-intensive. While prior works focus on training parallelization (e.g., data ...

In-memory deep neural network (DNN) accelerators will be the key for energy-efficient autonomous edge systems. The resistive random access memory (ReRAM) is a potential solution for the non-CMOS-based in-memory computing platform for energy-efficient ...