检索结果-内蒙古大学图书馆

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Shuyuan Sun Fan Yang Bei Yu Li Shang Xuan Zeng State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China and School of Microelectronics Fudan University Shanghai China Chinese University of Hong Kong Hong Kong China State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China and China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798350323481

Inverse Lithography Technology (ILT) is a widely investigated method to improve the yield of chip manufacturing. However, high computational complexity and difficulty in fabricating curvilinear shapes have hindered the widespread adoption of ILT. This paper presents an efficient ILT framework, including a multi-level resolution method for simulation acceleration, a downsampling strategy for mask optimization, and an improved mask binary function to improve mask printability. Experimental results show that the proposed method outperforms state-of-the-art methods with at least a 33.8% reduction in L2 loss and a 15.5% reduction in PVBand.

关键词：

来源：评论

学校读者我要写书评

暂无评论

通过深度神经网络与皮层网络的多级整合增强自然感知的神经编码模型

引用

science Bulletin 2024年第11期69卷 1738-1747页

作者：李远宁杨虎铮顾实 School of Biomedical Engineering&State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech UniversityShanghai 201210China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Department of Computer and Information Science University of PennsylvaniaPhiladelphiaPA 19104USA Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhen 518110China

Cognitive neuroscience aims to develop computational models that can accurately predict and explain neural responses to sensory inputs in the cortex. Recent studies attempt to leverage the representation power of deep neural networks(DNNs) to predict the brain response and suggest a correspondence between artificial and biological neural networks in their feature representations. However, typical voxel-wise encoding models tend to rely on specific networks designed for computer vision tasks, leading to suboptimal brain-wide correspondence during cognitive tasks. To address this challenge, this work proposes a novel approach that upgrades voxel-wise encoding models through multi-level integration of features from DNNs and information from brain networks. Our approach combines DNN feature-level ensemble learning and brain atlas-level model integration, resulting in significant improvements in predicting whole-brain neural activity during naturalistic video perception. Furthermore, this multi-level integration framework enables a deeper understanding of the brain's neural representation mechanism, accurately predicting the neural response to complex visual concepts. We demonstrate that neural encoding models can be optimized by leveraging a framework that integrates both data-driven approaches and theoretical insights into the functional structure of the cortical networks.

关键词： Neural encoding Visual perception Artificial neural networks Functional neuroimaging Naturalistic stimuli

来源：评论

学校读者我要写书评

暂无评论

A New Prediction Strategy for Dynamic Multi-objective Optimization Using Diffusion Model

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Wang, Feng Xie, Jinsong Zhou, Aimin Tang, Ke Wuhan University School of Computer Science Hubei430072 China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing The Department of Computer Science and Technology Shanghai200241 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

To solve dynamic multi-objective optimization problems (DMOPs), the optimization algorithms are required to track the movement of the Pareto set after the environmental changes effectively. Many prediction-based dynamic multi-objective evolutionary algorithms (DMOEAs) have been proposed to address this challenge by utilizing environmental information for population reinitialization. However, when environmental changes are complex, irregular, and severe, the solutions and information during the evolution process often contain noise, making it difficult for prediction-based DMOEAs to accurately predict and reinitialize the population. To address this issue, we propose a novel dynamic multi-objective evolutionary algorithm (DM-DMOEA) which uses a diffusion model based prediction strategy. In DM-DMOEA, to improve the prediction accuracy, the diffusion model is introduced to extract the relationships of high-quality solutions and reinitialize the population, and a PS estimation method is employed to integrate both historical and new environmental information, providing a set of high-quality solutions for diffusion model training. To speed up the response time, a variational autoencoder (VAE) is used to map the decision space to a latent space, which can reduce the diffusion model size and accelerate the diffusion process. To evaluate the effectiveness of the proposed DM-DMOEA on DMOPs, comprehensive experiments are conducted on several benchmarks and a practical problem. The results show that the DM-DMOEA outperforms other four state-of-the-art DMOEAs in most cases. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

引用

computers, Materials & Continua 2022年第8期72卷 3247-3267页

作者： Xinghai Ju Jicang Lu Xiangyang Luo Gang Zhou Shiyu Wang Shunhang Li Yang Yang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001China School of Computing and Information Systems Singapore Management University188065Singapore College of Computer Science and Big Data Fuzhou UniversityFuzhou350116China

For Internet forum Points of Interest(PoI),existing analysis methods are usually lack of usability analysis under different conditions and ignore the long-term variation,which lead to blindness in method *** address this problem,this paper proposed a PoI variation prediction framework based on similarity analysis between long and short *** on the framework,this paper presented 5 PoI analysis algorithms which can be categorized into 2 types,i.e.,the traditional sequence analysis methods such as autoregressive integrated moving average model(ARIMA),support vector regressor(SVR),and the deep learning methods such as convolutional neural network(CNN),long-short term memory network(LSTM),Transformer(TRM).Specifically,this paper firstly divides observed data into long and short windows,and extracts key words as PoI of each ***,the PoI similarities between long and short windows are calculated for training and ***,series of experiments is conducted based on real Internet forum *** results show that,all the 5 algorithms could predict PoI variations well,which indicate effectiveness of the proposed *** the length of long window is small,traditional methods perform better,and SVR is the *** the contrary,the deep learning methods show superiority,and LSTM performs *** results could provide beneficial references for PoI variation analysis and prediction algorithms selection under different parameter configurations.

关键词： Point of interest(PoI)analysis long and short windows sequential analysis deep learning

来源：评论

学校读者我要写书评

暂无评论

NPV: Fast Network Policy Verification for Cloud-Native Networking

NPV: Fast Network Policy Verification for Cloud-Native Netwo...

引用

International Conference on Distributed Computing Systems

作者： Shunbin Dong Yumin Xie Jin Zhao Kun Qiu School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Network policy plays a crucial role in cloud-native networking, especially in multi-tenant scenarios. It provides precise control over connectivity by specifying source and destination endpoints, traffic types, and other criteria to allow or deny traffic. However, manual configuration of these policies introduces the risk of errors, leading to isolation violations or network service unavailability. Therefore, network policy verification is essential for maintaining security and quality of service in cloud-native networking. Currently, a naïve approach involves individually checking each policy within the cluster, which can take over 100s for verification in a cluster size of over 100k. Existing verification frameworks, like Kano and Verikube, improve performance by leveraging pre-filtering and Satisfiability Modulo Theories (SMT) solvers, achieving a 3.12x to 12.99x performance boost over the naïve baseline. However, as network policy changes rapidly within 100ms in real cloud-native networks, both frameworks need over 10s to perform verification for cluster sizes over 100k, which is far from satisfying. To overcome these issues, we propose and implement a novel network policy verification framework NPV, which utilizes the policy-label pre-filter process with bitwise compression. We further enhance the policy verification algorithm with a policy-namespace divide-and-conquer strategy to improve the data-level parallelism. We implement NPV on commodity servers and evaluate its performance using real network policy datasets. Our experiments indicate that, compared with the state-of-the-art methods, NPV can achieve up to 139.00x to 651.06x improvement in verification time compared to Kano and Verikube, with 65% less memory usage.

关键词： Memory management Clustering algorithms Quality of service Manuals Parallel processing Servers Security

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Natural Man–Machine Interaction Technology and Its Application for Lunar Robot 23rd

Multi-modal Natural Man–Machine Interaction Technology and ...

引用

23rd IFToMM China International Conference on Mechanism and Machine science and Engineering, IFToMM CCMMS 2022

作者： Chen, Meng Zhang, Chongfeng Qin, Xiaofei Ma, Jia Zhang, Wenqi Shanghai Key Laboratory of Spacecraft Mechanism Shanghai201108 China Institute of Aerospace System Engineering Shanghai Shanghai201109 China Shanghai Academy of Spaceflight Technology Shanghai201109 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789811993978

For the requirements of multi-modal man–machine interaction between astronauts and robots in lunar surface exploration, research on three interaction modes and test system based on speech, body posture and tactile recognition are carried out. An improved speech feature classification and recognition algorithm based on Mel-scale Frequency Cepstral Coefficients (MFCC), a three-stage body posture recognition algorithm based on target detection—node recognition—skeleton action recognition, and a tactile recognition algorithm based on Radial Basis Function network (RBF) are proposed. In the body posture recognition algorithm, a lightweight CVC-Net model is developed based on the classical HourglassNet algorithm. Deep separable convolution, attention mechanism and improved up-sampling method are introduced. A lightweight network and adaptive graph convolution module for skeleton action recognition are designed by introducing the information of human body joints and skeleton vectors. Above algorithm is suitable for the embedded computing platform and can greatly reduce the number of module parameters while ensuring the detection accuracy. Based on the simulated lunar surface environment, lunar robot and simulated space suit, the ground test verification of three modes of command recognition is realized, which can meet the low power consumption, lightweight and real-time requirements of lunar robot for recognition algorithms and the embedded computing platform. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Reward Modeling Requires Automatic Adjustment Based on data Quality

Reward Modeling Requires Automatic Adjustment Based on Data ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wang, Binghai Zheng, Rui Chen, Lu Xi, Zhiheng Shen, Wei Zhou, Yuhao Yan, Dong Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Baichuan Inc. Beijing China Institute of Modern Languages and Linguistics Fudan University China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798891761681

In Reinforcement Learning from Human Feedback (RLHF), the reward model plays a crucial role in aligning language model outputs with human values. The human preference data used to train the reward model consists of a prompt and a response pair, with humans annotating which response better aligns with human value preferences. Due to the complexity and subjectivity of the annotation task, multiple organizations including OpenAI and Anthropic report significant noise in the human preference datasets, leading to instability and deviation in reward model training from human values. We discover that the difference in scores assigned to response pairs by the reward model effectively indicates the quality of data, and data of varying qualities show significant distinctions in reward model training. We introduce a method that automatically adjusts reward modeling based on data quality, reducing the impact of noise and making full use of dataset. Experiments on multiple human preference datasets demonstrate that our method stabilizes reward model training and significantly enhances the alignment performance of RLHF. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phenotyping of Salvia miltiorrhiza Roots Reveals Associations between Root Traits and Bioactive Components

引用

Plant Phenomics 2023年第4期5卷 746-756页

作者： Junfeng Chen Yun Wang Peng Di Yulong Wu Shi Qiu Zongyou Lv Yuqi Qiao Yajing Li Jingfu Tan Weixu Chen Ma Yu Ping Wei Ying Xiao Wansheng Chen The SATCM Key Laboratory for New Resources&Quality Evaluation of Chinese Medicine Institute of Chinese Materia MedicaShanghai University of Traditional Chinese MedicineShanghai 201203China School of Medicine Shanghai UniversityShanghai 200444China State Local Joint Engineering Research Center of Ginseng Breeding and Application Jilin Agricultural UniversityChangchun 130118China School of Computer Science Sichuan Normal UniversityChengdu 610066China Shangyao Huayu(Linyi)Traditional Chinese Resources Co. Ltd.Linyi 276000China School of Life Science and Engineering Southwest University of Science and TechnologyMianyang 621010SichuanChina Sichuan Academy of Traditional Chinese Medicine Chengdu 610041China Department of Pharmacy Changzheng HospitalSecond Military Medical UniversityShanghai 200003China

Plant phenomics aims to perform high-throughput,rapid,and accurate measurement of plant traits,facilitating the identification of desirable traits and optimal genotypes for crop *** miltiorrhiza(Danshen)roots possess remarkable therapeutic effect on cardiovascular diseases,with huge market *** great advances have been made in metabolic studies of the bioactive metabolites,investigation for *** roots on other physiological aspects is ***,we developed a framework that utilizes image feature extraction software for in-depth phenotyping of *** *** employing multiple software programs,*** roots were described from 3 aspects:agronomic traits,anatomy traits,and root system *** K-means clustering based on the diameter ranges of each root branch,all roots were categorized into 3 groups,with primary root-associated key *** a proof of concept,we examined the phenotypic components in a series of randomly collected *** roots,demonstrating that the total surface of root was the best parameter for the biomass prediction with high linear regression correlation(R^(2)=0.8312),which was sufficient for subsequently estimating the production of bioactive metabolites without content *** study provides an important approach for further grading of medicinal materials and breeding practices.

关键词： Root utilize anatomy

来源：评论

学校读者我要写书评

暂无评论

Instance-Aware Diffusion Implicit Process for Box-Based Instance Segmentation 26

Instance-Aware Diffusion Implicit Process for Box-Based Inst...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Ren, Hao Liu, Xingsong Huang, Junjian Wan, Ru Pu, Jian Lu, Hong Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-inspired Intelligence Fudan University China Mogo.ai Information and Technology Co. Ltd. Shanghai China

ISBN: (纸本)9781643684369

The diffusion model has demonstrated impressive performance in image generation, but its potential for discriminative tasks such as instance segmentation remains unexplored. In this paper, we propose an Instance-aware Diffusion Implicit Process (IDIP) framework for instance segmentation based on boxes. During training, IDIP diffuses ground-truth boxes across various time steps, extracting corresponding Region of Interest (RoI) features. Dynamic convolution is then used to predict boxes and categories for each RoI, and the mask head generates masks from these predictions. During inference, IDIP iteratively refines randomly generated boxes with the denoising diffusion implicit model, while the mask head derives final masks from RoIs based on the refined boxes. Our method surpasses existing approaches on the COCO benchmark, requiring fewer training steps and less memory resources due to its dynamic design and instance-aware characteristic. © 2023 The Authors.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：