检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics (ICMLC)

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

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

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.

关键词： White blood cells Training Deep learning Adaptation models Neural networks Focusing Vectors data models Medical diagnosis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual Information 48

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual Information Pre-trained Language Model

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 24

HairDiffusion: vivid multi-colored hair editing via latent d...

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

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

ISBN: (纸本)9798331314385

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language

arXiv

引用

arXiv 2025年

作者： Ariai, Farid Mahmoudi, Maryam Tayefeh Moeini, Ali Department of Computer Engineering University of Tehran Kish International Campus Kish Iran Data Analysis & Processing Research Group IT Research Faculty ICT Research Institute Tehran Iran School of Engineering Science College of Engineering University of Tehran Tehran Iran

In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming to amplify the efficiency of language models tailored to the Persian language. Focusing on enhancing the effectiveness of sentiment analysis, our approach employs an aspect-based methodology utilizing the ParsBERT model, augmented with a relevant lexicon. The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala.' The experimental results not only highlight the proposed method's superior semantic capabilities but also showcase its efficiency gains with an accuracy of 88.2% and an F1 score of 61.7. The importance of enhancing language models in this context lies in their pivotal role in extracting nuanced sentiments from user-generated content, ultimately advancing the field of sentiment analysis in Persian text mining by increasing efficiency and accuracy. © 2025, CC BY.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Large-Area Ag/Cu Pastes Sintering on Cu Base Plates for Power Module Packaging

Large-Area Ag/Cu Pastes Sintering on Cu Base Plates for Powe...

引用

International Conference on Electronics Packaging (ICEP)

作者： Chin-Hao Tsai Felix Steiner Dai Ishikawa C. Robert Kao Thomas Blank Institute for Data Processing and Engineering Karlsruhe Institute of Technology Germany Department of Materials Science and Engineering National Taiwan University Inorganic Materials Research Dept. Resonac Corporation Ltd. Japan

In this research, Ag, Cu, mixed Ag-In, and mixed Ag-SAC sinter pastes are used for large-area bonding in second-level power module packaging. Due to the large sintering area, different patterns with/without drying channels are tested in the pressure/pressureless sinter process. Besides, various bonding conditions, such as temperature and pressure, are investigated. To analyze large-area sintering effects, scanning acoustic microscopy is used to observe the interface of joints. Finally, the reliability of the large area sintered joints is assessed by thermal shock and bending tests. To conclude, this study explores the feasibility of multiple sintering pastes for large-area sintering. The results reveal that these pastes exhibit reliable properties under proper bonding conditions.

关键词： Printing Microscopy Sintering Thermal shock Multichip modules Bending Reliability

来源：评论

学校读者我要写书评

暂无评论

Research on energy consumption prediction of public buildings based on improved support vector machine

Research on energy consumption prediction of public building...

引用

第35届中国控制与决策会议

作者： Liyao Yang Hongyan Ma Yingda Zhang Shengyan Li School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big DataBeijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

An improved support vector machine model for energy consumption prediction is proposed to achieve efficient energy saving in *** this paper,firstly,a gray correlation analysis model is used to measure the correlation between temperature,humidity,sunlight and other factors and building energy ***,the sparrow search algorithm(SSA) is introduced to optimize the penalty coefficient c and kernel function parameter g of the support vector machine,and then the SSA-SVM energy consumption prediction model is ***,the experimental results are analyzed by comparing with the data derived from the support vector machine prediction(SVM) model and BP neural network energy consumption *** experimental results show that compared with SVM and BP neural network,the prediction results of SSA-SVM model perform better in error index,indicating that the energy consumption prediction of SSA-SVM model has higher prediction accuracy;the maximum relative error of SSA-SVM prediction model is 0.0514,and the maximum relative errors of the other two models are greater than 0.55,indicating that SSA-SVM model has a higher degree of reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a clever carbon monoxide monitoring system

Design of a clever carbon monoxide monitoring system

引用

第35届中国控制与决策会议

作者： Yanxi Cao Hongyan Ma Yingda Zhang Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big DataBeijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

Carbon monoxide is a colorless and odorless gas that is extremely *** monoxide cannot be accurately detected or eliminated by the senses in high concentrations in the body under relatively airtight *** a result,the human body can only inhale it *** monoxide inhalation can deplete the body's oxygen supply,causing symptoms such as nausea,dizziness,headaches,and,in severe cases,*** response to the event's insidiousness,urgency,and ***,because the current carbon monoxide monitoring system is not portable,it is proposed to design a microcontroller as the core,with a concentration collection module,a wireless transmission module,an LCD module,and so *** with information between intelligent monitoring systems via wireless transmission module and mobile phone *** system consists of a microcontroller,concentration acquisition module,wireless transmission module,and LCD display *** the performance of the system is tested by changing the environmental conditions,while a control test is *** results show that the system has a fast and stable transmission rate,small size,and wireless monitoring *** can be informed of environmental conditions via their mobile phones,providing early warning and quick alarms.

关键词： Wi-Fi transmission carbon monoxide monitoring microcontroller unit indoor real-time monitoring

来源：评论

学校读者我要写书评

暂无评论

Application of Computer Software Simulation in Building Fire Evacuation engineering:A Case Study of a University Library in Beijing

Application of Computer Software Simulation in Building Fire...

引用

第35届中国控制与决策会议

作者： Shun Wang Hongyan Ma Shengyan Li Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big DataBeijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

University library is an important building for teaching and *** atrium library has the characteristics of good lighting and flexible use,and the atrium structure was extensively ***,the fire in the atrium library will cause more serious *** this paper,we build a fire and evacuation model of a university atrium library and conduct a simulation *** with BIM technology,we restored the physical information of a university library and establish a fire *** was used to simulate the fire somke diffusion,and the smoke factors were analyzed to derive the available safe evacuation time(ASET).Pathfinder was used to simulate personnel evacuation,which determines the required safe evacuation time(REST).The simulation results show that the visibility of the smoke is the most important factor affecting personnel evacuation,and the personnel needs 108 s to evacuate the fire area and 291 s to enter the stairwell to *** the personnel in the library by area can shorten the evacuation time by about 74 *** study is expected to provide support for the fire simulation and personnel evacuation in atrium building.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：