检索结果-内蒙古大学图书馆

Intelligent control of mode-locked femtosecond pulses by time-stretch-assisted real-time spectral analysis

学校读者我要写书评

暂无评论

Light(science & Applications) 2020年第1期9卷 1881-1888页

作者： Guoqing Pu Lilin Yi Li Zhang Chao Luo Zhaohui Li Weisheng Hu State Key Lab of Advanced Communication Systems and Networks Shanghai Institute for Advanced Communication and Data ScienceShanghai Jiao Tong UniversityShanghai 200240China Sun Yat-sen University/Southern Marine Science and Engineering Guangdong Laboratory ZhuhaiChina

Mode-locked fiber lasers based on nonlinear polarization evolution can generate femtosecond pulses with different pulse widths and rich spectral distributions for versatile applications through polarization ***,a precise and repeatable location of a specific pulsation regime is extremely ***,by using fast spectral analysis based on a time-stretched dispersion Fourier transform as the spectral discrimination criterion,along with an intelligent polarization search algorithm,for the first time,we achieved real-time control of the spectral width and shape of mode-locked femtosecond pulses;the spectral width can be tuned from 10 to 40 nm with a resolution of ~1.47 nm,and the spectral shape can be programmed to be hyperbolic secant or ***,we reveal the complex,repeatable transition dynamics of the spectrum broadening of femtosecond pulses,including five middle phases,which provides deep insight into ultrashort pulse formation that cannot be observed with traditional mode-locked lasers.

关键词： polarization tuning spectral

Design and Simulation of Multi-tiered Heterogeneous Memory Architecture

学校读者我要写书评

暂无评论

Design and Simulation of Multi-tiered Heterogeneous Memory A...

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)

作者： Jinyuan Hu Haikun Liu Hai Jin Xiaofei Liao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Heterogeneous memory systems have become increasingly popular in recent years. Because heterogeneous storage media often show significantly different characteristics in terms of bandwidth, latency, capacity, and energy consumption, it is still challenging to best utilize them for cost-efficient and energy-efficient heterogeneous memory systems. In this paper, we propose a simulation framework for multi-tiered heterogeneous memory architectures based on GEM5 and DRAMsim3 simulators. We design a heterogeneous memory controller to architect Non-Volatile Memory (NVM) as main memory, and architect both Dynamic Random Access Memory (DRAM) and High-Bandwidth Memory (HBM) as a hybrid cache of NVM. Specifically, HBM, DRAM, and NVM are managed in a single (flat) address space. However, we use an address remapping table to maintain the mappings between NVM pages and HBM/DRAM pages, and logically manage HBM/DRAM/NVM as a three-tiered hybrid memory system. We also design a hardware-supported hot page monitor based on Majority Element Algorithm (MEA) to identify the hottest pages in the DRAM, and a dynamic threshold adjustment scheme for hot page migration to balance the memory bandwidth between DRAM and HBM. Our multi-tiered heterogeneous memory architecture can take advantage of the large capacity of NVM, the low latency of DRAM, and the high bandwidth of HBM concurrently. Experimental results show that our tiered memory architecture can improve application performance by an average of $2.5\times$ compared with an NVM-only architecture, and up to 57.4% compared with a DRAM-only architecture. Moreover, the performance gap between our HBM/DRAM/NVM architecture and a HBM-only architecture is less than 10%.

关键词： Analytical models Nonvolatile memory Heuristic algorithms Computational modeling Memory architecture Random access memory Computer architecture

CPSAA: Accelerating Sparse Attention using Crossbar-based Processing-In-Memory Architecture

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Huize Jin, Hai Zheng, Long Liao, Xiaofei Huang, Yu Liu, Cong Xu, Jiahong Duan, Zhuohui Chen, Dan Gui, Chuangyi National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

The attention-based neural network attracts great interest due to its excellent accuracy enhancement. However, the attention mechanism requires huge computational efforts to process unnecessary calculations, significantly limiting the system’s performance. To reduce the unnecessary calculations, researchers propose sparse attention to convert some dense-dense matrices multiplication (DDMM) operations to sampled dense-dense matrix multiplication (SDDMM) and sparse matrix multiplication (SpMM) operations. However, current sparse attention solutions introduce massive off-chip random memory access since the sparse attention matrix is generally unstructured. We propose CPSAA, a novel crossbar-based processing-in-memory (PIM)-featured sparse attention accelerator to eliminate off-chip data transmissions. First, we present a novel attention calculation mode to balance the crossbar writing and crossbar processing latency. Second, we design a novel PIM-based sparsity pruning architecture to eliminate the pruning phase’s off-chip data transfers. Finally, we present novel crossbar-based SDDMM and SpMM methods to process unstructured sparse attention matrices by coupling two types of crossbar arrays. Experimental results show that CPSAA has an average of 89.6×, 32.2×, 17.8×, 3.39×, and 3.84× performance improvement and 755.6×, 55.3×, 21.3×, 5.7×, and 4.9× energy-saving when compare with GPU, FPGA, SANGER, ReBERT, and ReTransformer. Copyright © 2022, The Authors. All rights reserved.

关键词： Memory architecture

InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xulong Dong, Siyan Zheng, Youyi Yang, Yanchao State Key Lab of CAD&CG Zhejiang University China Chohotech Co. Ltd. China Institute of Data Science The University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

3D surface reconstruction from multi-view images is essential for scene understanding and interaction. However, complex indoor scenes pose challenges such as ambiguity due to limited observations. Recent implicit surface representations, such as Neural Radiance Fields (NeRFs) and signed distance functions (SDFs), employ various geometric priors to resolve the lack of observed information. Nevertheless, their performance heavily depends on the quality of the pre-trained geometry estimation models. To ease such dependence, we propose regularizing the geometric modeling by explicitly encouraging the mutual information among surface normals of highly correlated scene points. In this way, the geometry learning process is modulated by the second-order correlations from noisy (first-order) geometric priors, thus eliminating the bias due to poor generalization. Additionally, we introduce a simple yet effective scheme that utilizes semantic and geometric features to identify correlated points, enhancing their mutual information accordingly. The proposed technique can serve as a plugin for SDF-based neural surface representations. Our experiments demonstrate the effectiveness of the proposed in improving the surface reconstruction quality of major states of the arts. Our code is available at: https://***/Muliphein/InfoNorm. Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

Impact of Crowdsourced Speed Check data on Traffic Speed: A Case Study of the Netherlands

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Liu, Yutian Bahrami, Sina Feng, Tao de Vries, Jorn Department of Built Environment Eindhoven University of Technology Eindhoven Netherlands Urban and Data Science Lab Graduate School of Advanced Science and Engineering Hiroshima University Japan Flitsmeister Veenendaal Netherlands

The proliferation of smartphones and internet connectivity has provided the opportunity of using crowdsourced data in traffic management. Nowadays, many people use navigation apps such as Google Maps, Waze, and Flitsmeister to obtain real-time travel information and provide feedback on road conditions such as reporting police speed checks. As an accurate traffic speed prediction is of great significance for road users and traffic managers, different models have been proposed and widely used to predict traffic speed considering spatio-temporal dependence of traffic data and external factors such as weather, accident and point of interest. This study investigates the impact of crowdsourced data about police enforcement from navigation apps on traffic speed. In addition, we examine whether the police enforcement report affects the accuracy of the deep learning prediction model. We extract crowdsourced police enforcement information from navigation apps, collect the corresponding historical traffic speed data, and predict traffic speed in several corridors in the Netherlands using a GCN-GRU traffic speed prediction model. The results show that the crowdsourced data for police enforcement causes the average vehicle speed to drop between 1 [km/h] to 3 [km/h] when passing the road segments marked with police activity. Moreover, the prediction performance of the GCN-GRU model during the periods without police enforcement is better than the periods with reported police activity showing that police speed check reports can decrease the accuracy of speed prediction models. © 2022, The Authors. All rights reserved.

关键词： Navigation

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

Tackling Noisy labels with Network Parameter Additive Decomposition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jingyi Xia, Xiaobo Lan, Long Wu, Xinghao Yu, Jun Yang, Wenjing Han, Bo Liu, Tongliang The Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha410073 China The Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Automation University of Science and Technology of China Hefei230026 China The Department of Computer Science Hong Kong Baptist University Hong Kong

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage. In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e. , parameters w are decomposed as w = σ + γ. Afterward, the parameters σ are considered to memorize clean data, while the parameters γ are considered to memorize mislabeled data. Benefiting from the memorization effect, the updates of the parameters σ are encouraged to fully memorize clean data in early training, and then discouraged with the increase of training epochs to reduce interference of mislabeled data. The updates of the parameters γ are the opposite. In testing, only the parameters σ are employed to enhance generalization. Extensive experiments on both simulated and real-world benchmarks confirm the superior performance of our method. The implementation is available at: https://***/wangjingyi9924/TNLPAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active Learning Under Noisy Crowd

International Conference on data engineering

作者： Wentao Zhang Yexin Wang Zhenbang You Yang Li Gang Cao Zhi Yang Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications Key Lab of High Confidence Software Technologies Peking University Department of Data Platform TEG Tencent Inc. Beijing Academy of Artificial Intelligence Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed.

关键词： Crowdsourcing Costs Noise Predictive models Graph neural networks labeling Noise measurement

Leveraging Unlabeled data for 3D Medical Image Segmentation Through Self-Supervised Contrastive Learning

学校读者我要写书评

暂无评论

Leveraging Unlabeled Data for 3D Medical Image Segmentation ...

IEEE International Symposium on Biomedical Imaging

作者： Sanaz Karimijafarbigloo Reza Azad Yury Velichko Ulas Bagci Dorit Merhof Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Machine and Hybrid Intelligence Lab Northwestern University Chicago IL USA Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these challenges, we introduce two distinct subnetworks designed to explore and exploit the discrepancies between them, ultimately correcting the erroneous prediction results. More specifically, we identify regions of inconsistent predictions and initiate a targeted verification training process. This procedure strategically fine-tunes and harmonizes the predictions of the subnetworks, leading to enhanced utilization of contextual information. Furthermore, to adaptively fine-tune the network’s representational capacity and reduce prediction uncertainty, we employ a self-supervised contrastive learning paradigm. For this, we use the network’s confidence to distinguish between reliable and unreliable predictions. The model is then trained to effectively minimize unreliable predictions. Our experimental results for organ segmentation, obtained from clinical MRI and CT scans, demonstrate the effectiveness of our approach when compared to state-of-the-art methods. The codebase is accessible on GitHub.

关键词： Training Three-dimensional displays Uncertainty Magnetic resonance imaging Computed tomography Semantic segmentation Contrastive learning