检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Zihao Chen Fan Yang Li Shang Xuan Zeng State Key Lab of ASIC & System School of Microelectronics Fudan University Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

This paper presents a neural architecture search scheme for chip layout hotspot detection. In this work, hotspot detectors, in the form of neural networks, are modeled as weighted directed acyclic graphs. A variational autoencoder maps the discrete graph topological space into a continuous embedding space. Bayesian Optimization performs neural architecture search in this embedding space, where an architecture performance predictor is employed to accelerate the search process. Experimental studies on ICCAD 2012 and ICCAD 2019 Contest benchmarks demonstrate that, the proposed scheme significantly improves the agility of previous neural architecture search schemes, and generates hotspot detectors with competitive detection accuracy, false alarm rate, and inference time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

TOTAL: Topology Optimization of Operational Amplifier via Reinforcement Learning

TOTAL: Topology Optimization of Operational Amplifier via Re...

引用

IEEE International Symposium on Quality Electronic Design

作者： Zihao Chen Songlei Meng Fan Yang Li Shang Xuan Zeng State Key Lab of ASIC & System School of Microelectronics Fudan University Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

With ever-increasing design complexity and stringent time-to-market pressure, automated topology synthesis tools for operational amplifiers are required to produce designs meeting different specifications. This paper proposes TOTAL, a reinforcement learning-based topology optimization method for operational amplifiers. We decompose the circuit topology design as a Markov decision process to solve the high dimensionality of the design space, with the three-stage cascode paradigm fixed to avoid meaningless structures. Therefore, starting from a basic behavior-level topology, an agent modifies the circuit step by step. Specifically, this agent mainly adopts a graph neural network to understand each design state, including specifications and the design history, and a convolutional neural network to modify the current topology. Every completed circuit is then simulated and evaluated by a customized reward function to guide the agent in finding qualified circuits, among which only the optimal one ever recorded is mapped to the transistor level for further evaluation. Experimental results show that the trained agent can not only generate high-performance circuits, but also be reusable by transferring to other specifications as a pre-trained model and achieving competitive results.

关键词： Operational amplifiers Circuit topology Network topology Optimization methods Reinforcement learning Markov processes Topology

来源：评论

学校读者我要写书评

暂无评论

Right Frontal Gamma Transcranial Alternating Current Stimulation Modulates Optimism Biases

引用

Neuroscience Bulletin 2025年第1期41卷 172-176页

作者： Ziqing Yao Jinwen Wei Gan Huang Linling Li Zhen Liang Li Zhang Haiyan Wu Tifei Yuan Zhiguo Zhang Xiaoqing Hu Department of Psychology The State Key Laboratory of Brain and Cognitive SciencesThe University of Hong KongHong KongSARChina School of Biomedical Engineering Medical SchoolShenzhen UniversityShenzhen518060China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen UniversityShenzhen518060China Centre for Cognitive and Brain Sciences and Department of Psychology University of MacaoMacao SARChina Shanghai Key Laboratory of Psychotic Disorders Brain Health InstituteNational Center for Mental DisordersShanghai Mental Health CenterShanghai Jiaotong University School of MedicineShanghai210109China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China Peng Cheng Laboratory Shenzhen518055China HKU-Shenzhen Institute of Research and Innovation Shenzhen518063China

Dear Editor,People are often optimistic when forecasting the future,such that they believe they are less likely to encounter adverse life *** phenomenon,known as optimism bias,emerges due to preferential encoding and consolidation of desirable over undesirable information[1,2],engaging frontal brain regions such as the anterior cingulate cortex and inferior frontal gyrus[1].An optimism bias is instrumental in supporting mental health:reduction or absence of optimism biases is associated with mood disorders such as depression,characterized by pessimistic thinking about the future[3].This relationship highlights the potential value of interventions that could enhance optimism bias[4].

关键词： ism such likely

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search 31

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Yuan, Ziming Dai, Lei Li, Wen Zhang, Jie Liang, Shengwen Wang, Ying Liu, Cheng Li, Huawei Li, Xiaowei Guo, Jiafeng Wang, Peng Chen, Renhai Zhang, Gong Shanxi University School of Computer and Information Technology China Peking University School of Computer Science China Institute of Computing Technology CAS State Key Lab of Processors China University of Chinese Academy of Sciences China Zhongguancun National Laboratory Beijing China Institute of Computing Technology CAS Key Lab of Network Data Science and Technology China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9798331506476

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

The Role of Depth, Width, and Tree Size in Expressiveness of Deep Forest 27

The Role of Depth, Width, and Tree Size in Expressiveness of...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Lyu, Shen-Huan Wu, Jin-Hui Zheng, Qin-Cheng Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University China College of Computer Science and Software Engineering Hohai University China National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9781643685489

Random forests are classical ensemble algorithms that construct multiple randomized decision trees and aggregate their predictions using naive averaging. Zhou and Feng [51] further propose a deep forest algorithm with multi-layer forests, which outperforms random forests in various tasks. The performance of deep forests is related to three hyperparameters in practice: depth, width, and tree size, but little has been known about its theoretical explanation. This work provides the first upper and lower bounds on the approximation complexity of deep forests concerning the three hyperparameters. Our results confirm the distinctive role of depth, which can exponentially enhance the expressiveness of deep forests compared with width and tree size. Experiments validate these theoretical findings. The detailed proof and code are available in the full version [31]. © 2024 The Authors.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Facial Micro-Motion-Aware Mixup for Micro-Expression Recognition

Facial Micro-Motion-Aware Mixup for Micro-Expression Recogni...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhuoyao Gu Miao Pang Zhen Xing Weimin Tan Xuhao Jiang Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

data-driven learning models have demonstrated strong benefits in capturing subtle facial movements for micro-expression recognition (MER), but are limited by the available data. Generative models can generate a variety of new data, but are typically computationally prohibitive compared to efficient Mixup-like methods. In this paper, we propose a novel Facial Micro-Motion-Aware Mixup approach for MER, namely MEMix. Our MEMix constructs a micro-motion-aware mask to select the most salient facial motions and generate a new sample with a mixed motion feature. This mixed motion feature can effectively expand the data distribution, leading to smoother decision boundaries for MER models. To demonstrate the good generality of MEMix, we integrate it with three advanced vision transformer-based models. The results show that the three integrated models consistently achieve performance improvements ranging from 4.07% to 7.32% in accuracy and from 6.54% to 9.18% in F1-score. Besides, to further explore the ability of MEMix, we propose a two-stream network called MixMeFormer, which unlocks the potential of the transformer by simply integrating mixed motion features with facial semantics for MER. Extensive experiments demonstrate that our MixMeFormer outperforms other state-of-the-art methods on three well-known micro-expression datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Guided Constraint Differential Evolution Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1109-1133页

作者： Sung, Tien-Wen Liang, Qiaoxin Hong, Chuanbo Huang, Zeming Li, Wei Nguyen, Trinh-Dong College of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China School of Electronic Electrical Engineering and Physics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China Department of Software Engineering University of Information Technology Ho Chi Minh City Viet Nam

The development of population intelligence has shown a great trend of a linear surge in recent years, and a large number of intelligent algorithms inspired by biology have been studied. Among them, differential evolution (DE) algorithms have attracted the attention of many researchers because of their simplicity, high efficiency, powerful search capability, etc. DE has strong exploitability and can approach the global optimum faster, but it cannot avoid the phenomenon of search stagnation and premature convergence. To address the drawbacks of DE, the two-stage bootstrap constrained differential evolution algorithm (TSGCDE) is proposed in this paper. In TSGCDE, instead of the traditional one population, the population is divided into two as a way to increase the diversity of the population. Divided into two stages, each stage searches for optimal solutions in different directions in different populations, and the optimal solutions and the bootstrap solutions generated by the populations in the two stages are bounded by each other’s bootstrap, which makes the DE have a more powerful optimal-seeking ability and easier to jump out of the local optimum. To validate the performance of TSGCDE, we conducted experiments on CEC2013 and CEC2014 benchmarks with some well-known algorithm variants, and the experimental results show that our proposed algorithm is competitive. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Denoising Diffusion Pre-training for Whole-Slide Image Classification 24

Multi-modal Denoising Diffusion Pre-training for Whole-Slide...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Lou, Wei Li, Guanbin Wan, Xiang Li, Haofeng The Chinese University of Hong Kong Shenzhen Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen China

ISBN: (纸本)9798400706868

Whole-slide image (WSI) classification methods play a crucial role in tumor diagnosis. Most of them use hematoxylin and eosin (H&E) stained images, while Immunohistochemistry (IHC) staining provides molecular markers and protein expression information that highlights cancer regions. However, obtaining IHC-stained images requires higher costs in practice. In this work, we propose a multi-modal denoising diffusion pre-training framework that harnesses the advantages of IHC staining to learn visual representations. The framework is trained with the H&E-to-IHC re-staining task and IHC-stained image reconstruction task, which helps capture the structural similarity and staining difference between two image modalities. The trained model can then provide IHC-guided features, by taking only H&E-stained images as inputs. Besides, we build a new class-constraint constrastive loss to achieve the semantic consistency between dual-modal features from our pre-training framework. To integrate with WSI classifiers based on multi-instance learning, we further propose a bag feature augmentation strategy to extend bags with the features extracted by our pre-trained model. Experimental results on three datasets show that our pre-training framework effectively improves WSI classification and surpasses the state-of-the-art pre-training approaches. Code and model are released via https://***/lhaof/MDDP. © 2024 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Magnetar emergence in a peculiar gamma-ray burst from a compact star merger

引用

National science Review 2025年第3期12卷 125-131页

作者： Hui Sun Chenwei Wang Jun Yang Bin-Bin Zhang Shaolin Xiong Yi-Han Iris Yin Yuan Liu Ye Li Wangchen Xue Zhen-Yu Yan Chen Zhang Wenjun Tan Haiwu Pan Jiacong Liu Huaqing Cheng Yanqiu Zhang Jingwei Hu Chao Zheng Zhenghua An Ce Cai Zhiming Cai Lei Hu Chichuan Jin Dongyue Li Xinqiao Li Heyang Liu Mingjun Liu Wenxi Peng Liming Song Shengli Sun Xiaojin Sun Xilu Wang Xiangyang Wen Shuo Xiao Shuxu Yi Fan Zhang Wenda Zhang Xiaofeng Zhang Yonghe Zhang Donghua Zhao Shijie Zheng Zhixing Ling Shuang-Nan Zhang Weimin Yuan Bing Zhang National Astronomical Observatories Chinese Academy of Sciences Key Laboratory of Particle Astrophysics Institute of High Energy Physics Chinese Academy of Sciences University of Chinese Academy of Sciences Chinese Academy of Sciences School of Astronomy and Space Science Nanjing University Key Laboratory of Modern Astronomy and Astrophysics (Nanjing University) Ministry of Education Purple Mountain Observatory Chinese Academy of Sciences College of Physics and Hebei Key Laboratory of Photophysics Research and Application Hebei Normal University Innovation Academy for Microsatellites Chinese Academy of Sciences Shanghai Institute of Technical Physics Chinese Academy of Sciences Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University Nevada Center for Astrophysics University of Nevada Department of Physics and Astronomy University of Nevada

The central engine that powers gamma-ray bursts（GRBs）, the most powerful explosions in the universe, is still not identified. Besides hyper-accreting black holes, rapidly spinning and highly magnetized neutron stars, known as millisecond magnetars, have been suggested to power both long and short GRBs. The presence of a magnetar engine following compact star mergers is of particular interest as it would provide essential constraints on the poorly understood equation of state for neutron stars. Indirect indications of a magnetar engine in these merger sources have been observed in the form of plateau features present in the X-ray afterglow light curves of some short GRBs. Additionally, some X-ray transients lacking gamma-ray bursts have been identified as potential magnetar candidates originating from compact star ***, smoking-gun evidence is still lacking for a magnetar engine in short GRBs, and associated theoretical challenges have been raised. Here we present a comprehensive analysis of the broad-band prompt emission data of the peculiar, very bright GRB 230307A. Despite its apparently long duration, the prompt emission and host galaxy properties are consistent with a compact star merger origin, as suggested by its association with a kilonova. Intriguingly, an extended X-ray emission component shows up as theγ-ray emission dies out, signifying the likely emergence of a magnetar central engine. We also identify an achromatic temporal break in the high-energy band during the prompt emission phase, which was never observed in previous bursts and reveals a narrow jet with a half opening angle of ~ 3.4°(RGRB/1015cm)-1/2,where RGRBis the GRB prompt emission radius.

关键词： gamma-ray burst magnetar X-ray emission compact binary merger

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：