Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it. Current leading graph models require a large number of labeled ...
详细信息
The underlying control for the hybrid energy storage system (HESS) in pure electric vehicles (PEVs) is crucial. System modeling is inherently subject to uncertainties due to fluctuations in electrical parameters and u...
详细信息
The promotion of quantum network applications demands the scalable connection of quantum *** is preferable to set up multiple logical networks coexisting on a single physical network infrastructure to accommodate a la...
详细信息
The promotion of quantum network applications demands the scalable connection of quantum *** is preferable to set up multiple logical networks coexisting on a single physical network infrastructure to accommodate a larger number of *** we present a quantum virtual network architecture that offers this level of scalability,without being constrained to a fixed physical-layer network relying solely on passive multiplexing *** architecture can be understood as arising from the superposition of a fully connected entanglement distribution network and port-based virtual local area network,which group multiusers by access *** terms of hardware,we leverage a semiconductor chip with a high figure-of-merit modal overlap to directly generate high-quality polarization entanglement,and a streamlined polarization analysis module,which requires only one single-photon detector for each end *** experimentally perform the BBM92 QKD protocol on the five-user quantum virtual network and demonstrate voice and image encryption on a campus area *** results may provide insights into the realization of large-scale quantum networks with integrated and cost-efficient photonic architecture.
Satisfactory progress has been achieved recently in universal segmentation of CT images. Following the success of vision-language methods, there is a growing trend towards utilizing text prompts and contrastive learni...
详细信息
Accurate polyp segmentation is crucial for early diagnosis and treatment of colorectal cancer. This is a challenging task for three main reasons: (i) the problem of model overfitting and weak generalization due to the...
详细信息
Accurate polyp segmentation is crucial for early diagnosis and treatment of colorectal cancer. This is a challenging task for three main reasons: (i) the problem of model overfitting and weak generalization due to the multi-center distribution of data;(ii) the problem of interclass ambiguity caused by motion blur and overexposure to endoscopic light;and (iii) the problem of intraclass inconsistency caused by the variety of morphologies and sizes of the same type of polyps. To address these challenges, we propose a new high-precision polyp segmentation framework, MEFA-Net, which consists of three modules, including the plug-and-play Mask Enhancement Module (MEG), Separable Path Attention Enhancement Module (SPAE), and Dynamic Global Attention Pool Module (DGAP). Specifically, firstly, the MEG module regionally masks the high-energy regions of the environment and polyps through a mask, which guides the model to rely on only a small amount of information to distinguish between polyps and background features, avoiding the model from overfitting the environmental information, and improving the robustness of the model. At the same time, this module can effectively counteract the "dark corner phenomenon" in the dataset and further improve the generalization performance of the model. Next, the SPAE module can effectively alleviate the inter-class fuzzy problem by strengthening the feature expression. Then, the DGAP module solves the intra-class inconsistency problem by extracting the invariance of scale, shape and position. Finally, we propose a new evaluation metric, MultiColoScore, for comprehensively evaluating the segmentation performance of the model on five datasets with different domains. We evaluated the new method quantitatively and qualitatively on five datasets using four metrics. Experimental results show that MEFA-Net significantly improves the accuracy of polyp segmentation and outperforms current state-of-the-art algorithms. Code posted on https://***/
Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate th...
Learning a model heavily depends on the training examples, which are sometimes difficult to obtain if not impossible. This a typically true for fault diagnosis in machinery, particularly for compound faults. The count...
详细信息
Offline Reinforcement Learning (RL) optimizes policy using pre-collected data instead of direct environment interaction, offering a safe and cost-effective solution for sequential decision-making in the real world. Ho...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Offline Reinforcement Learning (RL) optimizes policy using pre-collected data instead of direct environment interaction, offering a safe and cost-effective solution for sequential decision-making in the real world. However, it faces challenges such as distribution shift issues and vulnerability under perturbations. Researchers have developed various conservative methods to improve the robustness of offline RL. Nevertheless, model-based methods can result in transition distribution shift issues, while model-free value-based uncertainty penalty methods may not be sufficiently robust. To address these problems, we propose a new method called Robust Offline RL via Conservative Smoothing and Dynamics Controlling (RCSD). To achieve reliable value estimation of out-of-distribution (OOD) actions, RCSD uses both model-free uncertainty penalty and model-based simulation methods. It introduces a new one-step simulation method with conservative dynamics controlling to avoid value overestimation caused by transition distribution shifts. Moreover, RCSD considers both current and next states when generating OOD states to ensure cautious value estimation and efficient data utilization. RCSD uses conservative Q-smoothing and policy smoothing to strengthen the policy against sudden changes under perturbations. Experiments on D4RL benchmark demonstrate that RCSD can achieve state-of-the-art performance compared to baselines in either benchmark or adversarial attack tests.
Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used M...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements.
作者：
Zhao, WeiFeng, DanTong, WeiWei, XueliangWu, BingMinistry of Education of China
School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology China
Massive off-chip accesses in GPUs are the main performance bottleneck. We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are iden...
详细信息
暂无评论