检索结果-内蒙古大学图书馆

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Xia, Heming Yang, Zhe Dong, Qingxiu Wang, Peiyi Li, Yongqi Ge, Tao Liu, Tianyu Li, Wenjie Sui, Zhifang Department of Computing The Hong Kong Polytechnic University Hong Kong National Key Laboratory for Multimedia Information Processing Peking University China Microsoft Research Asia China Alibaba Group China

ISBN: (纸本)9798891760998

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts several future tokens efficiently and then verifies them in parallel. Unlike autoregressive decoding, Speculative Decoding facilitates the simultaneous decoding of multiple tokens per step, thereby accelerating inference. This paper presents a comprehensive overview and analysis of this promising decoding paradigm. We begin by providing a formal definition and formulation of Speculative Decoding. Then, we organize in-depth discussions on its key facets, such as drafter selection and verification strategies. Furthermore, we present a comparative analysis of leading methods under third-party testing environments. We aim for this work to serve as a catalyst for further research on Speculative Decoding, ultimately contributing to more efficient LLM inference. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A multi-strategy enhanced dung beetle algorithm for solving real-world engineering problems

引用

Artificial Intelligence Review 2025年第8期58卷 1-79页

作者： Mao, Zhengxing Yang, Zhen Luo, Dan Lin, Dong Jiang, Qinghong Huang, Guoxian Liao, Zhixian College of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Education Department of Guangxi Zhuang Autonomous Region Guilin541004 China Guilin University Guilin541006 China

The Dung Beetle optimization (DBO) algorithm is an innovative and effective metaheuristic algorithm widely recognised for its excellent numerical optimization performance. However, DBO converges slowly and tends to fall into local optima due to the imbalance between exploration and exploitation, the lack of collaborative search capability and population diversity. To overcome these challenges, this paper proposes a dung beetle optimization algorithm based on multi-strategy collaborative enhancement (MDBO). The algorithm constructs a "search-enhance-escape" collaborative optimization framework through adaptive regulation and elite information sharing, and contains three major innovations: (1) a dual adaptive search strategy, which combines the adaptive contraction mechanism of the leader’s centre of mass and the brownian bidirectional crossover perturbation strength regulation, to enhance the population diversity and collaborative search ability of the dung beetle, achieving a dynamic balance between exploration and exploitation;(2) Elite Enhanced Solution Quality (EESQ) mechanism, which improves the quality of both the current local and global optimal positions and accelerates convergence through structured elite information and dual-phase adaptive perturbation;and (3) Dynamic Oppositional Learning (DOL), which introduces an asymmetric adaptive perturbation in the dung beetle’s foraging and Breeding phases and enhances the ability to escape from local optima. The three act synergistically to achieve a more efficient optimised search. The performance of MDBO is evaluated using the IEEE CEC 2017, CEC 2019 and CEC 2020 benchmarking functions. Compared to the DBO algorithm, the MDBO algorithm improves the convergence accuracy and stability on the CEC2017 benchmark functions by 60.91 % and 63.98 %, respectively. For the CEC2019 benchmark functions, the corresponding improvements are 54.47 % and 41.36 %, while for the CEC2020 benchmark functions, they are 50.71 % and 55.1

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

A Sentiment Classification Model Based on Syntactic Graph Attention Networks 24

A Sentiment Classification Model Based on Syntactic Graph At...

引用

2024 International Conference on intelligent Education and Computer Technology, IECT 2024

作者： Cheng, Yan Zhou, Ziwei School of Computer Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Prov. Key Lab. of Intelligent Information Processing and Affective Computing of Jiangxi Province 330022 China School of Software Jiangxi Normal University 330022 China

ISBN: (纸本)9798400709920

Text Sentiment Classification, a significant task in Natural Language processing, aims to comprehend user needs and expectations by categorizing the sentiments of texts posted on platforms. Despite their utility, existing models for this task do not fully account for the influence of contextual and syntactic text features on sentiment classification. To address these issues, a text sentiment classification model based on syntactic graph attention network is proposed in this study. The model begins by extracting the contextual features of a sentence using BiGRU. It then generates a syntactic graph through a syntactic analyzer, using the contextual features as the node features of the syntactic graph. A syntactic graph attention network is constructed to extract the syntactic features of the syntactic graph. These feature vectors are then input into a softmax function to achieve text sentiment classification. Experimental results indicate that the proposed model outperforms similar models on two public datasets in terms of classification accuracy, thus demonstrating its effectiveness. © 2024 ACM.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

An Assisting Education System of Electronic Building Blocks Based on Deep Learning 24

An Assisting Education System of Electronic Building Blocks ...

引用

2024 7th International Conference on Computer information Science and Artificial Intelligence, CISAI 2024

作者： Shi, Zhuo Xu, Ziquan Qiu, Xia He, Haoen Luo, Xiaonan School of Art and Design Guilin University of Electronic Technology Guangxi Guilin China Guangxi Key Laboratory of lmage and Graphic Intelligent Processing Guangxi Guilin China Department of Computer and Information Security University of Guilin Electronic Technology Guangxi Guilin China Department of Guangxi Key Laboratory of Image and Graphic Intelligent Processing University of Guilin Electronic Technology Guangxi Guilin China

ISBN: (纸本)9798400707254

It is difficult for children to build electronic building blocks. In order to facilitate users to build building blocks, this paper designs and implements an electronic building block auxiliary system based on machine vision. The system uses the deep learning object detection model PP-YOLOv2 to detect the building block pictures taken by the user, obtain the location information of all the two-dimensional code in the pictures, and then decode the two-dimensional code, perform perspective transformation on the pictures, and obtain the final two-dimensional code decoding information and location information. Finally, the position of the QR code identified by the building blocks on the user’s picture is crossed and compared with the position of the standard building blocks, so as to determine whether the building blocks placed by the user are correct and give the user a prompt. The system test shows that the system is not only easy to use, but also easy to maintain, and can correctly handle most of the small and medium difficulty examples in the electronic building blocks course. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation Random Vector Functional Link for White Blood Cell Classification 23

Domain Adaptation Random Vector Functional Link for White Bl...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Wang, Qin Wang, Xi-Zhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen University The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9798331528041

There's growing recognition of how machine learning can revolutionize the precision and swiftness of clinical diagnoses by improving the classification of white blood cells. However, a machine learning model specialized in white blood cell classification demands access to a large trove of well-annotated data. This poses a challenge, as in the medical field, annotating data comprehensively comes with a high cost in terms of both money and time. To circumvent this, domain adaptation (DA) techniques are employed to leverage similar cell images from related domains, thereby boosting the model's performance in white blood cell classification in specific contexts. Among the myriad DA approaches available for this application, including TCA-based and deep learning methods, all typically suffer from lengthy training durations. Addressing this challenge, we introduce a novel DA method inspired by the random vector functional link (RVFL) network, a type of neural network characterized by its random weights. Our proposed method, named Domain Adaptation Random Vector Functional Link (DA-RVFL), capitalizes on the efficiency of RVFL networks to enhance white blood cell classification. This innovative approach shows some insights for future research in the efficient and effective classification of white blood cells. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Toward Comprehensive Semantic Prompt for Region Contrastive Learning Underwater Image Enhancement

Toward Comprehensive Semantic Prompt for Region Contrastive ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wang, Xiao Fu, Yongsheng Wang, Wei Liu, Wei School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China

ISBN: (纸本)9798350368741

Underwater image enhancement (UIE) focuses on mitigating image quality degradation due to light absorption and scattering. However, most existing methods enhance images via a global and uniform manner, neglecting the inherent semantic information in different regions, which may cause the network to easily deviate from the region's original color. Moreover, these methods typically rely on clear images to guide network convergence, a process constrained by the limited availability of real-world datasets, making it extremely challenging to train enhancement models for various degradations. To address these challenges, this paper introduces a semantic guidance and region contrastive constraints network (SRCNet). Initially, we propose a semantic-aware RWKV (Receptance Weighted key Value) block and a semantic prompt regularization module. These components leverage intra-target semantic correlations to preserve image details and colors within a global perceptual framework, while employing focal loss to emphasize the restoration of severely degraded regions. Subsequently, we introduce a region contrastive learning method that effectively utilizes negative samples to precisely capture features sensitive to degradation factors, thereby fostering robust feature distributions. Finally, experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. © 2025 IEEE.

关键词： contrastive learning rwkv semantic prompt Underwater image enhancement

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based FDTD Method for 3D Electromagnetic Simulation

Machine Learning Based FDTD Method for 3D Electromagnetic Si...

引用

2024 IEEE International Conference on Computational Electromagnetics, ICCEM 2024

作者： Dai, Jinpeng Xie, Guoda Hou, Guilin Zhang, Liyuan Huang, Zhixiang Anhui University The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Education of Anhui Province Anhui Province Key Laboratory of Target Recognition and Feature Extraction Anhui Luan237000 China Ministry of Education The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Institute of Energy Hefei Comprehensive National Science Center Hefei230031 China Institute of Plasma Physics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China Anhui Province Anhui University Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China Anhui University Hefei China

ISBN: (纸本)9798350383317

This article introduces an innovative and efficient deep learning-assisted Finite-Difference Time-Domain (DL-FDTD) method in the field of computational electromagnetics. This method ingeniously integrates the Gated Recurrent Unit (GRU) network and Particle Swarm Optimization (PSO) algorithm into the traditional FDTD framework, termed as the PSO-GRU-FDTD model. A key innovation of this model is the application of the particle swarm algorithm, which significantly simplifies the parameter tuning process, thereby accelerating model development. This advancement represents a notable breakthrough from the complex parameter adjustment process typical in traditional neural network models. Moreover, compared to the traditional Long Short-Term Memory (LSTM) networks, the GRU network excels in simplicity, convenience, and efficiency, while also ensuring accuracy. Ultimately, this method is applied to three-dimensional electromagnetic simulation and emulation. Numerical results demonstrate that this approach exhibits outstanding performance in both simulation accuracy and efficiency. © 2024 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

Research on financial social public opinion communication model based on variation mechanism 6

Research on financial social public opinion communication mo...

引用

6th International Conference on Electronic information Technology and Computer Engineering, EITCE 2022

作者： Huang, Maojun Hong, Mei Dong, Lin Yuan, Da Key Laboratory of Intelligent Information Processing Shandong Technology and Business University Shandong Yantai264005 China

ISBN: (纸本)9781450397148

In the context of rapid development of the Internet, the place of spreading financial public opinion is converted from traditional offline places to major online social platforms. Mastering the development mechanism of financial social opinion dissemination on online social media can effectively estimate the length of influence of public opinion and the scope of affected people, and provide effective guidance to relevant staff. Based on the Susceptible Infected Recovered Model, this paper divides the people involved in opinion diffusion into commenters and discussers, and introduces the variation mechanism to design the Susceptible-comment-discussion-removal model, then simulates the model to study the effects of different initial states and parameters on the model, and finally verifies the validity of the model by combining the real data of stock bars. The simulation experiments and validation show that the model can effectively describe the spread of public opinion among the user groups of financial social platforms when it occurs, and provide a valid reference for related workers. However, the content of public opinion, the personal influence of communicators, and the lag effect of communication all have an impact on communication, and these issues need to be addressed in future research. © 2022 Association for computing Machinery.

关键词： Social aspects

来源：评论

学校读者我要写书评

暂无评论

Beyond animal detection: A benchmark for detecting animal age group 5

Beyond animal detection: A benchmark for detecting animal ag...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhou, Hang Wu, You Li, Jiehong Pan, Liangtao Ye, Hengzhou Li, Shuiwang College of Information Science and Engineering Guilin University of Technology Guangxi Guilin541006 China Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing Guangxi Guilin541006 China

ISBN: (纸本)9781510668621

There are numerous practical applications for animal age estimation, such as age simulation, population structure estimation, wildlife conservation, biometrics, and more. Most of the current methods either concentrate solely on animal detection or animal age estimation. However, animal detection provides limited information, which is not adequate for more sophisticated computer vision tasks. On the other hand, existing methods for estimating animal age are based primarily on facial images, but capturing an accurate image of an animal’s face in a wild environment is extremely difficult and impractical for animals without discriminative facial features. In this paper, we propose a novel task, called Animal Age Group Detection. This task is a combination of animal detection and animal age estimation, with the primary goal of obtaining more information beyond the location of the animal by also providing crude age information, which is simple to accomplish with computer vision methods in a variety of open-world applications. To facilitate the study of this challenging, we present a benchmark for Animal Age Group Detection (AAGD), which contains a diverse range of 22 animal types, comprising a total of 4, 778 images. These images are well-annotated with axis-aligned bounding boxes and include information about the age groups of the animals. In addition, we establish a baseline detector for this task, called AG-YOLOF. The release of AAGD aims to facilitate future research on the identification of animal age groups and enhance awareness of this significant area of study. © 2023 SPIE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Exploiting Multi-Decision and Deep Refinement for Ultrasound Image Segmentation

Exploiting Multi-Decision and Deep Refinement for Ultrasound...

引用

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

作者： Wenjing Liu Xuanya Li Kai Hu Xieping Gao Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Baidu Inc Beijing China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China

In this paper, we propose a novel convolutional neural network (MDR-Net) for ultrasound image segmentation by exploiting multi-decision and deep refinement of the target. Our MDR-Net consists of two main parts, i.e., a multi-decision module (MDM) and a deep refinement module (DRM). Specifically, the MDM effectively addresses the issue of inconspicuous target regions in ultrasound images by combining multi-scale features and multi-receptive field self-attention to enhance the discriminative representation of features and diagnose feature points multiple times. In addition, to alleviate the problem of blurred boundaries and severe speckle noise, the DRM progressively fuses multi-scale features and makes the fused features interact with higher-level features to refine the target details step by step. Finally, we evaluate the proposed method on two publicly available datasets, namely BUSI and UDIAT. We achieve a Dice of 0.8265 and 0.8827 on the two datasets, which are at least 2% and 1.24% higher than other state-of-the-art ultrasound image segmentation methods.

关键词： Deep learning Image segmentation Visualization Ultrasonic imaging Fuses Neural networks Speckle

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：