检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Ge Yuan Xiaodong Cun Yong Zhang Maomao Li Chenyang Qi Xintao Wang Ying Shan Huicheng Zheng School of Computer Science and Engineering Sun Yat-sen University and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Key Laboratory of Information Security Technology and Tencent AI Lab Tencent AI Lab The Hong Kong University of Science and Technology School of Computer Science and Engineering Sun Yat-sen University and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Key Laboratory of Information Security Technology

Exquisite demand exists for customizing the pretrained large text-to-image model, e.g. Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original ones even given several images during training. We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just one facial photograph and only 1024 learnable parameters under 3 minutes. So we can effortlessly generate stunning images of this person in any pose or position, interacting with anyone and doing anything imaginable from text prompts. To achieve this, we first analyze and build a well-defined celeb basis from the embedding space of the pre-trained large text encoder. Then, given one facial photo as the target identity, we generate its own embedding by optimizing the weight of this basis and locking all other parameters. Empowered by the proposed celeb basis, the new identity in our customized model showcases a better concept combination ability than previous personalization methods. Besides, our model can also learn several new identities at once and interact with each other where the previous customization model fails to. Project page is at: http://***. Code is at: https://***/ygtxr1997/CelebBasis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of severity of Knee Osteoarthritis on X-ray images using deep learning

Prediction of severity of Knee Osteoarthritis on X-ray image...

引用

2022 IEEE North Karnataka Subsection Flagship International Conference, NKCon 2022

作者： Arumugam, Sajeev Ram Balakrishna, R. Rajeshram, V. Gowr, Sheela Karuppasamy, Sankar Ganesh Premnath, S.P. Sri Krishna College of Engineering and Technology Department of AI&DS Coimbatore India Dr. Sakunthala Engineering College Vel Tech High Tech Dr. Rangarajan Department of AI&DS Chennai India M.Kumarasamy College of Engineering Department of Computer Science and Engineering Karur India Department of CSE Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of CSE Chennai India Sri Krishna College of Engineering and Technology Department of ECE Coimbatore India

ISBN: (纸本)9781665453424

The most prevalent kind of arthritis is osteoarthritis (OA). Radiologists use to employ the Kellgren-Lawrence (KL) grading system to identify the aggressiveness of OA based on the information shown on the pair of knee joints. computer-assisted strategies have recently been proposed to enhance the accuracy of OA diagnosis. Previous semiautomatic segmentation approaches, on the other hand, required human interaction, limiting their use on huge datasets. Furthermore, CNN is used to quantify OA rigorousness to investigate the relationships among distinct local regions. SSD reduces human interaction and provides a back-to-back approach to computerized osteoarthritis detection by incorporating the object detection model. The rating is based on X-ray scans from the Osteoarthritis Initiative (Oai) dataset. At the cost of training on a huge dataset with over 8260 knee joint samples, our method accurately segments 96.37% of data. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multilevel Particle Filters for Partially Observed McKean-Vlasov Stochastic Differential Equations

arXiv

引用

arXiv 2024年

作者： Awadelkarim, Elsiddig Jasra, Ajay Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia School of Data Science The Chinese University of Hong Kong Shenzhen China

In this paper we consider the filtering problem associated to partially observed McKean-Vlasov stochastic differential equations (SDEs). The model consists of data that are observed at regular and discrete times and the objective is to compute the conditional expectation of (functionals) of the solutions of the SDE at the current time. This problem, even the ordinary SDE case is challenging and requires numerical approximations. Based upon the ideas in [3, 12] we develop a new particle filter (PF) and multilevel particle filter (MLPF) to approximate the afore-mentioned expectations. We prove under assumptions that, for ϵ > 0, to obtain a mean square error of O(ϵ2) the PF has a cost per-observation time of O(ϵ−5) and the MLPF costs O(ϵ−4) (best case) or O(ϵ−4 log(ϵ)2) (worst case). Our theoretical results are supported by numerical experiments. © 2024, CC BY.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

An Effective Customer Segmentation Approach to Improve E-Commerce Platform Quality Based on Intensive Learning Methodology

An Effective Customer Segmentation Approach to Improve E-Com...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Suresh, G.R. Vinoparkavi, D. Govindasamy, Suresh Rohini, S. Giri, Jayant Sabri, M. Omar Dhanalakshmi Srinivasan College of Engineering and Technology Department of Ece Mamallapuram Chennai India Nandha Engineering College Department of Cse Erode India Sona College of Technology Department of Electrical and Electronics Engineering Salem India R.M.K Engineering College Department of Computer Science Engineering Kavaraipettai Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Zarqa University Faculty of Economic Department of Business Information Technology Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

To accomplish company goals and reap advantages while satisfying and meeting consumer expectations, segmentation is an essential facilitator. Identifying subgroups of the target market that share common traits, requirements, and priorities is customer segmentation's primary goal. Various dataset dimensionalities are also considered, as are changes across time. In this study, we use time-based segmentation and clustering approaches to the e-commerce industry to conduct predictive neural network analysis using factors such as product reviews, goods, buying trend, watching pattern, and more. In this research, Intensive Neural Classification Learning (INCL) is presented as a novel deep learning technique. To assess its efficacy, it is cross-validated with the traditional Neural Network (NN) learning algorithm. We have evaluated unigrams, bigrams, and trigrams as part of the feature extraction process and identified the unique brands per consumer. In addition, the customer's chosen brands may be determined using a neural network, and the projected data can then be utilized for statistical analysis. We all know that sentiment analysis and categorization are huge help when trying to guess how customers feel about certain companies and items. Lastly, using the provided set of input data, we will choose the top brands by assessing the accuracy of the forecasts. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

TBIOM Special Issue on 'Best Reviewed Papers from IJCB 2020 - Editorial'

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity science 2021年第4期3卷 441-442页

作者： Ratha, Nalini Singh, Richa Struc, Vitomir Kakadiaris, Ioannis A. Phillips, Jonathon P. Vatsa, Mayank University at Buffalo BuffaloNY United States Department of Computer Science and Engineering Indian Institute of Technology Jheepasani Jodhpur India Department of Electrical Engineering University of Ljubljana Ljubljana Slovenia Department of Computer Science University of Houston HoustonTX United States Information Access Division National Institute of Standards and Technology GaithersburgMD United States

Recent years have seen considerable advances in biometric recognition techniques leading to a wide-spread deployment of biometric technology across a number of application domains, ranging from security, border control, and criminal investigations to entertainment, social media, autonomous driving and even health services. To highlight some of these advancements and present the latest research achievements related to biometrics, the 4th IEEE/IAPR International Joint Conference on Biometrics (IJCB) was organized in 2020. IJCB combines two major biometrics research conferences, the IEEE International Conference on Biometrics Theory, Applications and Systems (BTAS) conference, and the International Conference on Biometrics (ICB) and is made possible through a special agreement between the IEEE Biometrics Council and the IAPR TC-4. Because IJCB has (so far) only been organized every three years, it represents a particularly prestigious and selective event, where only the highest-quality research is presented.

关键词： Special issues and sections Meetings Face recognition Convolutional neural networks Tracking Iris recognition Biometrics (access control)

来源：评论

学校读者我要写书评

暂无评论

Almost Exact Recovery in Gossip Opinion Dynamics Over Stochastic Block Models

Almost Exact Recovery in Gossip Opinion Dynamics Over Stocha...

引用

IEEE Conference on Decision and Control

作者： Yu Xing Karl H. Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Digital Futures Stockholm Sweden

We study community detection based on state observations from gossip opinion dynamics over stochastic block models (SBM). It is assumed that a network is generated from a two-community SBM where each agent has a community label and each edge exists with probability depending on its endpoints' labels. A gossip process then evolves over the sampled network. We propose two algorithms to detect the communities out of a single trajectory of the process. It is shown that, when the influence of stubborn agents is small and the link probability within communities is large, an algorithm based on clustering transient agent states can achieve almost exact recovery of the communities. That is, the algorithm can recover all but a vanishing part of community labels with high probability. In contrast, when the influence of stubborn agents is large, another algorithm based on clustering time average of agent states can achieve almost exact recovery. Numerical experiments are given for illustration of the two algorithms and the theoretical results of the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Pretraining for Improving Diagnostic and Therapeutic Entity Recognition in Electronic Medical Records

Deep Neural Pretraining for Improving Diagnostic and Therape...

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： Shreya Patchala Enquero G Sunil Suvarna Sunil Kumar Chunduri Lavanya Prateeksha Siddhanti Global-A Genpact Company Bangalore India School of Computer Science & Artificial Intelligence SR University Warangal India IT Department Malla Reddy Engineering College for Women Hyderabad Dhulapally India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaadeswaram India Department of AI and ML Nitte Meenakshi Institute of Technology Bengaluru Yelahanka India

The predominance of compound agency, a lack of utterance components, and unclear entity boundaries all contribute to difficulties in distinguishing diagnostic and treatment entities in EMRs. Furthermore, obtaining electronic medical records in China may be difficult. A deep learning strategy that uses deep neural pretraining to improve diagnostic and therapeutic entity recognition in EMRs is proposed. A BERT-CRF model example is shown using a dataset of 10,000 EMRs. This paradigm combines the benefits of pretraining with the adaptability of CRF. The outcomes of the study show that deep brain pretraining might be used to improve the performance of NLP applications in the healthcare business. The use of a domain-specific corpus learning technique and an entity recognition model trained on a training dataset improves word embeddings. The suggested system achieved an accuracy (0.973), precision (0.909), recall (0.896), f1-score (0.902) and MCC (0.893) respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPQ Inventory Model with Backorders and Energy Implications

引用

IFAC-PapersOnLine 2023年第2期56卷 8598-8603页

作者： Hong-Nguyen Nguyen Matthieu Godichaud Lionel Amodeo Computer Sciences and Digital Society Laboratory (LIST3N) University of Technology of Troyes Troyes France Division of Industrial Engineering and Management The University of Danang - University of Science and Technology Danang Vietnam

With the scarcity of energy supply in the world and especially in the European region, energy price is soaring rapidly. Therefore, finding solutions to save energy is a top priority for manufacturers. This study introduces an EPQ inventory model that takes into account the correlation between production processes and energy consumption, while also allowing for backorders. The energy consumption during both production and non-production periods of the machine is computed. The energy consumption in EPQ policies is contingent upon the production rate and the machine's states (off or standby) during non-production phases. Utilizing the proposed resolution algorithm, the model under examination seeks to minimize the average total system cost while considering the production rate, cycle time, the initial production time of the cycle, and the optimal machine state during non-production periods. To demonstrate the formulated model, a numerical analysis is conducted, with a particular focus on the impact of allowing backorders.

关键词： Economic production quantity (EPQ) Inventory management Sustainable manufacturing Energy consumption Backordering

来源：评论

学校读者我要写书评

暂无评论

A THEORY OF INITIALISATION’S IMPACT ON SPECIALISATION

arXiv

引用

arXiv 2025年

作者： Jarvis, Devon Lee, Sebastian Dominé, Clémentine Carla Juliette Saxe, Andrew M. Mannelli, Stefano Sarao School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa Center for Computational Neuroscience Flatiron Institute Simons Foundation Gatsby Computational Neuroscience Unit Sainsbury Wellcome Centre UCL United Kingdom Data Science and AI Computer Science and Engineering Chalmers University of Technology University of Gothenburg Sweden Machine Intelligence and Neural Discovery Institute University of the Witwatersrand South Africa CIFAR Azrieli Global Scholar CIFAR

Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of catastrophic interference. This phenomenon is attributed to the network’s tendency to reuse learned features across tasks. However, this explanation heavily relies on the premise that neuron specialisation occurs, i.e. the emergence of localised representations. Our investigation challenges the validity of this assumption. Using theoretical frameworks for the analysis of neural networks, we show a strong dependence of specialisation on the initial condition. More precisely, we show that weight imbalance and high weight entropy can favour specialised solutions. We then apply these insights in the context of continual learning, first showing the emergence of a monotonic relation between task-similarity and forgetting in non-specialised networks. Finally, we show that specialization by weight imbalance is beneficial on the commonly employed elastic weight consolidation regularisation technique. Copyright © 2025, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Quantum Circuit Synthesis with Machine Learning

arXiv

引用

arXiv 2023年

作者： Weiden, Mathias Younis, Ed Kalloor, Justin Kubiatowicz, John Iancu, Costin Department of Electrical Engineering and Computer Science University of California Berkeley United States Computational Research Division Lawrence Berkeley National Laboratory United States

In the Noisy Intermediate Scale Quantum (NISQ) era, finding implementations of quantum algorithms that minimize the number of expensive and error prone multi-qubit gates is vital to ensure computations produce meaningful outputs. Unitary synthesis, the process of finding a quantum circuit that implements some target unitary matrix, is able to solve this problem optimally in many cases. However, current bottom-up unitary synthesis algorithms are limited by their exponentially growing run times. We show how applying machine learning to unitary datasets permits drastic speedups for synthesis algorithms. This paper presents QSeed, a seeded synthesis algorithm that employs a learned model to quickly propose resource efficient circuit implementations of unitaries. QSeed maintains low gate counts and offers a speedup of 3.7× in synthesis time over the state of the art for a 64 qubit modular exponentiation circuit, a core component in Shor's factoring algorithm. QSeed's performance improvements also generalize to families of circuits not seen during the training process. © 2023, CC BY.

关键词： Machine 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：