检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kim, Jinuk El Halabi, Marwa Ji, Mingi Song, Hyun Oh Department of Computer Science and Engineering Seoul National University Korea Republic of Neural Processing Research Center Samsung SAIT AI Lab Montreal Canada Google. United States

Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback;the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speedup while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://***/snu-mllab/LayerMerge. Copyright © 2024, The Authors. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Methodological Insights in Detecting Subtle Semantic Shifts with Contextualized and Static Language Models

Methodological Insights in Detecting Subtle Semantic Shifts ...

引用

2023 Findings of the Association for Computational Linguistics: EMNLP 2023

作者： Hoeken, Sanne Alaçam, Özge Fokkens, Antske Sommerauer, Pia Computational Linguistics Dept. of Linguistics Bielefeld University Germany Center for Information and Language Processing LMU Munich Germany Computational Linguistics & Text Mining Lab Vrije Universiteit Amsterdam Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands

ISBN: (纸本)9798891760615

In this paper, we investigate automatic detection of subtle semantic shifts between social communities of different political convictions in Dutch and English. We perform a methodological study comparing methods using static and contextualized language models. We investigate the impact of specializing contextualized models through fine-tuning on target corpora, word sense disambiguation and sentiment. We furthermore propose a new approach using masked token prediction which relies on behavioral information, specifically the most probable substitutions, instead of geometrical comparison of representations. Our results show that methods using static models and our masked token prediction method can detect differences in connotation of politically loaded terms, whereas methods that rely on measuring the distance between contextualized representations are not providing clear signals, even in synthetic scenarios of extreme shifts. © 2023 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Guo, Kuo Li, Yifan Chen, Hao Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai200240 China Carnegie Mellon University School of Computer Science Computational Biology Department PittsburghPA15213 United States

ISBN: (纸本)9798350337488

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function. © 2023 IEEE.

关键词： alternative splicing gene ontology heterogeneous graph attention network isoform function prediction protein language model

来源：评论

学校读者我要写书评

暂无评论

Korean-Chinese Bilingual Sentence Alignment Method Based on Character Length 2nd

Korean-Chinese Bilingual Sentence Alignment Method Based on ...

引用

2nd Big Data Analytics for Cyber-Physical System in Smart City, BDCPS 2020

作者： Wang, Qi Zhao, Yahui Cui, Rongyi Intelligent Information Processing Lab. Department of Computer Science and Technology Yanbian University Yanji133002 China

ISBN: (纸本)9789813345737

Sentence-level aligned bilingual parallel corpus is an indispensable and valuable resource for machine translation, translation knowledge acquisition, and bilingual dictionary compilation. Based on the Korean-Chinese parallel corpus, this paper uses a Korean-Chinese sentence alignment algorithm based on character length to realize automatic Korean-Chinese sentence alignment, and proposes a sentence alignment evaluation method. Firstly, preprocess and segment the Korean-Chinese corpus;Secondly, calculate the mean and variance of the corpus distribution based on the Korean Chinese corpus, and use the probability score to find the maximum likelihood probability of the sentence under the framework of dynamic programming;Finally, proposed a sentence alignment judgment method, with the help of Hanjaja tool to convert Sino-Korean words in Korean sentences into Chinese words to form Korean sentences containing Chinese words (abbreviated as C-K sentences), then calculate the Jaccard coefficient between the C-K sentence and the Chinese sentence, by determining the appropriate threshold to automatically determine the alignment or not. Experiments show that the length-based sentence alignment method has a good effect on automatic alignment of Korean-Chinese sentences, and the accuracy of sentence alignment reaches 88.61%. The proposed sentence alignment judgment method is simple and effective. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Device-Simulation-Based Machine Learning Technique and Performance Optimization of NSFET

Device-Simulation-Based Machine Learning Technique and Perfo...

引用

information Technology (OCIT), OITS International Conference on

作者： Ummadisetti Gowthami Bhuvanagiri Venkata Naga Sandhya Patta Supraja Sanjay Kumar Matta Durga Prakash Department of Electronics and Communication Engineering SRM University-AP Guntur India Department of Computer Science and Engineering Visual Information Processing Lab SRM University Guntur AP India

ISBN: (数字)9798331510404

ISBN: (纸本)9798331510411

With the rapid growth of the semiconductor industry, it is clear that device simulation has been considered as slow process. As a result of semiconductor device downscaling, obtaining the inevitable device simulation data is significantly more expensive because it requires complex analysis of multiple factors. Using Machine Learning (ML) techniques to device modeling is promising, as their combination will lead to great outcomes in the semiconductor industry. Nanosheet Field Effect Transistor (NSFET) is a promising device for high-performance integrated circuits due to their superior electrical control and reduced short-channel effects. This paper presents a ML based Nanosheet Field Effect Transistor modeling. In traditional Technology computer-Aided Design (TCAD) simulation, at once only a single simulation of NSFET for fixed length, width and thickness can be done, for change in any of the input parameter again simulation has to be done. To overcome this, simultaneous changes in input parameters are predicted using machine learning. The length, width, and thickness of the dielectric layer are input parameters and the drain current is the output parameter for the ML-based device model for NSFET. Experimental results have shown that our ML-based model can predict drain current accurately. $\mathrm{R}^{2}$ -value is found be around 0.99832. The highest $\mathrm{I}_{\text{ON}}/\mathrm{I}_{\text{OFF}}$ ratio, very high ON current (ION), very low OFF current (IOFF) is achieved for NSFET. The primary goal of this work is to explore the possibility of ML model that can replace the device simulation to reduce the computational cost and drive energy-efficient devices.

关键词： Machine learning algorithms Design automation Computational modeling Semiconductor devices Field effect transistors Electronics industry Prediction algorithms Nanoscale devices Integrated circuit modeling Tuning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Device Modeling and Performance Optimization for OTFT

Machine Learning-Based Device Modeling and Performance Optim...

引用

information Technology (OCIT), OITS International Conference on

作者： Prasanthi Lingala Bethalam Venkata Siva Sai Greeshma Patta Supraja Sanjay Kumar Matta Durga Prakash Department of Electronics and Communication Engineering SRM University- AP Guntur India Department of Computer Science and Engineering Visual Information Processing Lab SRM University- AP Guntur India

ISBN: (数字)9798331510404

ISBN: (纸本)9798331510411

In the huge growth of semiconductor industry, it is noticed that the device simulation is a very sluggish process. It is very promising to use Machine Learning (ML) techniques in device modeling as their combination will create great results in semiconductor industry and reduce the computational time. Organic Thin Film Transistor (OTFT) is a promising alternative to amorphous silicon devices due to its flexibility, low cost, and can be manufactured at reduced temperatures. In traditional TCAD simulation, at once only a single simulation of OTFT for fixed length, width and dielectric thickness can be done, for change in any of the input parameter again simulation has to be done. To avoid this ML is used to predict drain current for simultaneous changes in input parameters. This introduces a machine learning based structure to model OTFT integrated with ML algorithm named Random Forest Regressor (RFR). ML based device model for p-type OTFT takes length, width and thickness of dielectric layer as input parameters and drain current as output parameter. Experimental results has shown that our ML-based model can predict drain current accurately. $\mathbf{R}^{2}$ -value is found be around 0.997253. ML based performance optimization is a promising alternative to traditional technology computer aided design (TCAD) tools. The highest $\mathbf{I}_{\text{ON}}/\mathbf{I}_{\text{OFF}}$ ratio, very high ON current (I ON ), very low OFF current (I OFF ) is achieved for OTFT. $\mathbf{I}_{\text{ON}}/\mathbf{I}_{\text{OFF}}$ ratio is obtained to be 10 11 . The trained RFR models can accelerate the optimization in terms of performance and serves as promising alternative.

关键词： Machine learning algorithms Computational modeling Semiconductor devices Electronics industry Prediction algorithms Organic thin film transistors Dielectrics Optimization Tuning Random forests

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Maximization in RISs-Assisted UAVs-Based Edge Computing Network Using Deep Reinforcement Learning

引用

Big Data Mining and Analytics 2024年第4期7卷 1065-1083页

作者： Chuanwen Luo Jian Zhang Jianxiong Guo Yi Hong Zhibo Chen Shuyang Gu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083Chinaand also with the Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland AdministrationBeijing 100083China Advanced Institute of Natural Sciences Beijing Normal UniversityZhuhai 519087Chinaand also with the Guangdong Key Lab of AI and Multi-Modal Data ProcessingBNU-HKBU United International CollegeZhuhai 519087China Department of Computer Information Systems Texas A&M University-Central TexasKilleenTX 76549USA

Edge Computing(EC)pushes computational capability to the Terrestrial Devices(TDs),providing more efficient and faster computing *** Aerial Vehicles(UAVs)equipped with EC servers can be flexibly deployed,even in complex terrains,to provide mobile computing services at all ***,UAVs can establish an air-to-ground line-of-sight link with TDs to improve the quality of communication ***,the UAV-to-TD link may be obstructed by ground obstacles such as buildings or trees,leading to sub-optimal data transmission *** surmount this issue,Reconfigurable Intelligent Surfaces(RISs)emerge as a promising technology capable of intelligently reflecting signals to enhance communication quality between UAVs and *** this paper,we consider the RISs-assisted multi-UAVs collaborative edge Computing Network(RUCN)in urban environment,in which we study the computational offloading *** goal is to maximize the overall energy efficiency of UAVs by jointly optimizing the flight duration and trajectories of UAVs,and the phase shifts of *** is worth noting that this problem has been formally established as ***,we propose the Deep Deterministic Policy Gradients based UAV Trajectory and RIS Phase shift optimization algorithm(UTRP-DDPG)to solve this complex optimization *** results of extensive numerical experiments show that the proposed algorithm outperforms the other benchmark algorithms under various parameter ***,the UTRP-DDPG algorithm improves the UAV energy efficiency by at least 2%compared to DQN algorithm.

关键词： edge computing computing offloading Unmanned Aerial Vehicle(UAV) Reconfigurable Intelligent Surface(RIS) deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Device-Simulation-Based Machine Learning Technique and performance optimization of NSFET 22

Device-Simulation-Based Machine Learning Technique and perfo...

引用

22nd OITS International Conference on information Technology, OCIT 2024

作者： Gowthami, Ummadisetti Sandhya, Bhuvanagiri Venkata Naga Supraja, Patta Kumar, Sanjay Prakash, Matta Durga Department of Electronics and Communication Engineering SRM University- AP Guntur India Visual Information Processing Lab Department of Computer Science and Engineering SRM University- AP Guntur India

ISBN: (纸本)9798331510404

With the rapid growth of the semiconductor industry, it is clear that device simulation has been considered as slow process. As a result of semiconductor device downscaling, obtaining the inevitable device simulation data is significantly more expensive because it requires complex analysis of multiple factors. Using Machine Learning (ML) techniques to device modeling is promising, as their combination will lead to great outcomes in the semiconductor industry. Nanosheet Field Effect Transistor (NSFET) is a promising device for high-performance integrated circuits due to their superior electrical control and reduced short-channel effects. This paper presents a ML based Nanosheet Field Effect Transistor modeling. In traditional Technology computer-Aided Design (TCAD) simulation, at once only a single simulation of NSFET for fixed length, width and thickness can be done, for change in any of the input parameter again simulation has to be done. To overcome this, simultaneous changes in input parameters are predicted using machine learning. The length, width, and thickness of the dielectric layer are input parameters and the drain current is the output parameter for the ML-based device model for NSFET. Experimental results have shown that our ML-based model can predict drain current accurately. R2-value is found be around 0.99832. The highest ION/IOFF ratio, very high ON current (ION), very low OFF current (IOFF) is achieved for NSFET. The primary goal of this work is to explore the possibility of ML model that can replace the device simulation to reduce the computational cost and drive energy-efficient devices. © 2024 IEEE.

关键词： Nanosheets

来源：评论

学校读者我要写书评

暂无评论

EXLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models

arXiv

引用

arXiv 2025年

作者： Zheng, Kangjie Yang, Junwei Liang, Siyue Feng, Bin Liu, Zequn Ju, Wei Xiao, Zhiping Zhang, Ming School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University Anker Embodied AI Lab Peking University China Shenzhen China College of Computer Science Sichuan University Chengdu China Computer Science and Engineering Department University of Washington United States

Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input sequences with [MASK] tokens and learning to reconstruct the original content based on the remaining context. This paper explores the impact of [MASK] tokens on MLMs. Analytical studies show that masking tokens can introduce the corrupted semantics problem, wherein the corrupted context may convey multiple, ambiguous meanings. This problem is also a key factor affecting the performance of MLMs on downstream tasks. Based on these findings, we propose a novel enhanced-context MLM, EXLM. Our approach expands [MASK] tokens in the input context and models the dependencies between these expanded states. This enhancement increases context capacity and enables the model to capture richer semantic information, effectively mitigating the corrupted semantics problem during pre-training. Experimental results demonstrate that EXLM achieves significant performance improvements in both text modeling and SMILES modeling tasks. Further analysis confirms that EXLM enriches semantic representations through context enhancement, and effectively reduces the semantic multimodality commonly observed in MLMs. © 2025, CC BY-NC-SA.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Graph neural Networks in Intelligent Transportation Systems: Advances, Applications and Trends

arXiv

引用

arXiv 2024年

作者： Li, Hourun Zhao, Yusheng Mao, Zhengyang Qin, Yifang Xiao, Zhiping Feng, Jiaqi Gu, Yiyang Ju, Wei Luo, Xiao Zhang, Ming School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University Anker Embodied AI Lab Peking University Beijing China Department of Computer Science University of California Los Angeles United States

Intelligent Transportation System (ITS) is crucial for improving traffic congestion, reducing accidents, optimizing urban planning, and more. However, the complexity of traffic networks has rendered traditional machine learning and statistical methods less effective. With the advent of artificial intelligence, deep learning frameworks have achieved remarkable progress across various fields and are now considered highly effective in many areas. Since 2019, Graph neural Networks (GNNs) have emerged as a particularly promising deep learning approach within the ITS domain, owing to their robust ability to model graph-structured data and address complex problems. Consequently, there has been increasing scholarly attention to the applications of GNNs in transportation, which have demonstrated excellent performance. Nevertheless, current research predominantly focuses on traffic forecasting, with other ITS domains, such as autonomous vehicles and demand prediction, receiving less attention. This paper aims to review the applications of GNNs across six representative and emerging ITS research areas: traffic forecasting, vehicle control system, traffic signal control, transportation safety, demand prediction, and parking management. We have examined a wide range of graph-related studies from 2018 to 2023, summarizing their methodologies, features, and contributions in detailed tables and lists. Additionally, we identify the challenges of applying GNNs in ITS and propose potential future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

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：