检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 18784-18850页

作者： Chengkuan Hong Christian R. Shelton Jun Zhu Department of Computer Science and Technology BNRist Center Tsinghua Institute for AI Tsinghua-Bosch Joint Center for ML Tsinghua University Beijing China Department of Computer Science and Engineering University of California Riverside CA

Neyman-Scott processes (NSPs) are a class of Cox processes constructed by stacking layers of Poisson processes into a deep structure. While a lot of research has been conducted regarding the posterior sampling and inference for NSPs, most of the existing methods only work for shallow NSPs (i.e., NSPs with one layer of latent Poisson processes). In this paper, we present virtual-event-based posterior sampling and inference algorithms for NSPs. The algorithms work for both deep NSPs and shallow NSPs. Moreover, we show that deep NSPs can be viewed as branching processes or a limiting case of probabilistic graphical models. We conduct a theoretical analysis of the convergence of our algorithms and provide the condition for the convergence to hold. In doing so, we also prove the convergence of virtual-event-based sampling inference algorithms for other point process models with missing information (Markov jump processes, piecewise-constant intensity models, and Hawkes processes). Like NSPs, the latent variables of these models with missing information are also point processes. Our experimental results demonstrate that the prediction based on our sampling and inference algorithms for NSPs can achieve good prediction performance compared with state-of-the-art methods.

关键词： Markov chain Monte Carlo variational inference point processes hierarchical model Neyman-Scott processes

来源：评论

学校读者我要写书评

暂无评论

Unmanned aerial vehicles: A review

引用

Cognitive robotics 2023年第1期3卷 8-22页

作者： Laghari, Asif Ali Jumani, Awais Khan Laghari, Rashid Ali Nawaz, Haque Department of Computer Science Sindh Madressatul Islam University Pakistan School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou China Interdisciplinary Research Center for Intelligent Manufacturing and Robotics King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia

The lightweight Unmanned Aerial Vehicle (UAV) flight activities are constrained, particularly in the UAV range or activity span and perseverance, by the strategic correspondence link capabilities. This paper tends to the different overlap issue of trading off a set of mission prerequisites, the UAV execution parameters, and strategic credibility;thus compromising between the communication load characterized by a crucial, communication link transmitting power necessities, power accessibility onboard UAV as a weight-restricted parameter, and the UAV security. © 2022

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Health Monitoring and Maintenance Scheduling for Nuclear Power Systems

Probabilistic Health Monitoring and Maintenance Scheduling f...

引用

aiAA Science and Technology Forum and Exposition, aiAA SciTech Forum 2025

作者： Amer, Ahmad Tsilifis, Panagiotis Saxena, Abhinav Baglietto, Emilio Khan, Genghis Probabilistic Design & Material Informatics GE Aerospace Research Niskayuna NY12309 United States Robotics AI & Computer Vision GE Vernova Advanced Research Niskayuna NY12309 United States AI & Computer Vision GE Aerospace Research San RamonCA94583 United States Department of Nuclear Science & Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Sustainable Systems GE Aerospace Research Niskayuna NY12309 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Operations and Maintenance (O&M) cost optimization in the nuclear energy industry is an imperative task for developing sustainable systems and efficient renewable technologies. We present a modular probabilistic framework for addressing maintenance scheduling challenges for small modular nuclear reactors using a Dynamic Bayesian Network (DBN) approach that monitors fatigue and performance in multiple subsystems of the reactors and provides a probabilistic assessment for potential failure events. The DBN framework fuses information from potential digital twins that assimilate real time data from several sensors with different time granularities in order to monitor and update thecurrentstate of knowledge aboutthestatus of several fatigue or performance criteria. Comprised of multi-modal digital twins (empirical, data- and physics-based twins), this DBN serves as a predictive framework forecasting the future state of specific reactor subsystems and enhancing decision-making capabilities associated with preventing system failure and minimizing the time and cost of maintenance events. The work presented in this paper is a holistic approach for monitoring and safeguarding complex, multi-component engineering systems where maintenance scheduling is critical and does not restrict itself to nuclear environments. However, our goal is to illustrate how such a framework can be adjusted to small modular water reactors. © 2025, American Institute of Aeronautics and Astronautics Inc, aiAA. All rights reserved.

关键词： Nuclear energy

来源：评论

学校读者我要写书评

暂无评论

Continual Facial Features Transfer for Facial Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Maharjan, Rahul Singh Bonicelli, Lorenzo Romeo, Marta Calderara, Simone Cangelosi, Angelo Cucchiara, Rita University of Manchester Centre for Robotics and Ai United Kingdom University of Modena and Reggio Emilia Department of Engineering Enzo Ferrari Modena Italy Heriot-Watt University Department of Computer Science United Kingdom

Facial Expression Recognition (FER) models based on deep learning mostly rely on a supervised train-once-test-all approach. These approaches assume that a model trained on an in-the-wild facial expression dataset with one type of domain distribution will perform well on a test dataset with a domain distribution shift. However, facial images in real-world can be from different domain distributions from which the model has been trained. However, re-training models on only new domain distributions will severely affect the performance of the previous domain. Re-training on all previous and new data can improve overall performance but is computationally expansive. In this study, we oppose the train-once-test-all approach and propose a buffer-based continual learning approach to enhance the performance of multiple in-the-wild datasets. We propose a model that continually leverages attention to important facial features from the pre-trained model to improve performance in multiple datasets. We validated our model using split-in-the-wild datasets where the dataset is provided to the model in an incremental setting instead of all at once. Furthermore, to evaluate the model performance, we continually used three in-the-wild datasets representing different domains (Domain-FER). Extensive experiments on these datasets reveal that the proposed model achieves better results than other Continual FER models. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Steering Angle Predictive Convolutional Neural Network for Autonomous Car

引用

computers, Materials & Continua 2022年第5期71卷 2285-2302页

作者： Hajira Saleem Faisal Riaz Asadullah Shaikh Khairan Rajab Adel Rajab Muhammad Akram Mana Saleh Al Reshan Control Automotive and Robotics Lab Affiliated lab of National Center of Robotics and Automation(NCRA HEC Pakistan)and with the Department of Computer Science and Information TechnologyMirpur University of Science and Technology(MUST)Mirpur Azad Kashmir10250Pakistan College of Computer Science and Information System Najran UniversityNajran61441Saudi Arabia College of Computer Science and Engineering University of South FloridaTampa33620United States

Deep learning techniques,particularly convolutional neural networks(CNNs),have exhibited remarkable performance in solving visionrelated problems,especially in unpredictable,dynamic,and challenging *** autonomous vehicles,imitation-learning-based steering angle prediction is viable due to the visual imagery comprehension of *** this regard,globally,researchers are currently focusing on the architectural design and optimization of the hyperparameters of CNNs to achieve the best *** has proven the superiority of metaheuristic algorithms over the manual-tuning of ***,to the best of our knowledge,these techniques are yet to be applied to address the problem of imitationlearning-based steering angle ***,in this study,we examine the application of the bat algorithm and particle swarm optimization algorithm for the optimization of the CNN model and its hyperparameters,which are employed to solve the steering angle prediction *** validate the performance of each hyperparameters’set and architectural parameters’set,we utilized the Udacity steering angle dataset and obtained the best results at the following hyperparameter set:optimizer,Adagrad;learning rate,0.0052;and nonlinear activation function,exponential linear *** per our findings,we determined that the deep learning models show better results but require more training epochs and time as compared to shallower *** show the superiority of our approach in optimizing CNNs through metaheuristic algorithms as compared with the manual-tuning *** testing was also performed using the model trained with the optimal architecture,which we developed using our approach.

关键词： Bat algorithm convolutional neural network hyperparameters metaheuristic optimization algorithm steering angle prediction

来源：评论

学校读者我要写书评

暂无评论

Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking

arXiv

引用

arXiv 2024年

作者： Acikgoz, Emre Can Erdoğan, Mete Yuret, Deniz Koç University KUIS AI Center Turkey Koç University Department of Computer Engineering Turkey

Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations, with a special focus on Turkish. We conduct an in-depth analysis to evaluate the impact of training strategies, model choices, and data availability on the performance of LLMs designed for underrepresented languages. Our approach includes two methodologies: (i) adapting existing LLMs originally pretrained in English to understand Turkish, and (ii) developing a model from the ground up using Turkish pretraining data, both supplemented with supervised fine-tuning on a novel Turkish instruction-tuning dataset aimed at enhancing reasoning capabilities. The relative performance of these methods is evaluated through the creation of a new leaderboard for Turkish LLMs, featuring benchmarks that assess different reasoning and knowledge skills. Furthermore, we conducted experiments on data and model scaling, both during pretraining and finetuning, simultaneously emphasizing the capacity for knowledge transfer across languages and addressing the challenges of catastrophic forgetting encountered during fine-tuning on a different language. Our goal is to offer a detailed guide for advancing the LLM framework in low-resource linguistic contexts, thereby making natural language processing (NLP) benefits more globally accessible. © 2024, CC BY-NC-SA.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Hard Gate Knowledge Distillation - Leverage Calibration for a Robust and Reliable Language Model

Hard Gate Knowledge Distillation - Leverage Calibration for ...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Lee, Dongkyu Tian, Zhiliang Zhao, Yingxiu Cheung, Ka Chun Zhang, Nevin L. Department of Computer Science and Engineering HKUST Hong Kong College of Computer National University of Defense Technology China NVIDIA AI Technology Center NVIDIA

In knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a teacher is considered a subject that holds inter-class relations which send a meaningful supervision to a student;hence, much effort has been put to find such knowledge to be distilled. In this paper, we explore a question that has been given little attention: "when to distill such knowledge." The question is answered in our work with the concept of model calibration;we view a teacher model not only as a source of knowledge but also as a gauge to detect miscalibration of a student. This simple and yet novel view leads to a hard gate knowledge distillation scheme that switches between learning from a teacher model and training data. We verify the gating mechanism in the context of natural language generation at both the token-level and the sentence-level. Empirical comparisons with strong baselines show that hard gate knowledge distillation not only improves model generalization, but also significantly lowers model calibration error. © 2022 Association for Computational Linguistics.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Novel Audio Mosaic Using LPC-Coefficient and Excitation-Codeword Permutations

引用

IEEE Signal Processing Letters 2024年 31卷 1690-1694页

作者： Tsai, Morris C.-H. Wu, Hsiao-Chun Huang, Scott C.-H. Chang, Shih Yu National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Taoyuan City32003 Taiwan San Jose State University Department of Applied Data Science San JoseCA95192 United States

In this letter, a novel light-weight audio mosaic scheme using permutations of linear predictive coding (LPC) coefficients as LPC has been widely adopted in many audio codecs (coder-encoders) nowadays. We establish the theoretical secrecy analysis with respect to the degree of the original LPC polynomial and the minimum-phase population of permuted LPC polynomials. The mosaic (destructuring) performance in terms of DCT-KLD (Kullback-Leibler divergence of discrete cosine transform) is also evaluated through simulations. In comparison with the existing audio-mosaic method using waveform permutations, our proposed new audio-mosaic scheme using LPC-coefficient permutations can achieve a much better mosaic performance (a much higher DCT-KLD) subject to the same key size. © 1994-2012 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Electrochemical impedance behavior of implantable neural interface following the change of equivalent circuit element 12

Electrochemical impedance behavior of implantable neural int...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Zhang, Jing Liu, Lusheng Wang, aiping Wang, Junkongshuai Fang, Tao Niu, Lan Bin, Jianxiong Wang, Pengchao Mu, Wei Jia, Jie Zhang, Lihua Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Moe Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu City322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

The simulation of two basic equivalent circuit models of the implantable neural interface is described in this paper. The simulated equivalent circuits are created based on the physicochemical mechanism of charge transfer on the surface of the implantable neural interface. Each parameter of the equivalent circuit model was varied to investigate the regular pattern of individual element affecting the performance of the implantable neural interface. In this paper, one circuit model is based on the charge transfer process, and another circuit model is based on the mixed charge transfer and diffusion process. The equivalent circuits are split into two parts. The neural interface of the implantable neural interface device is simulated in one part, and the rest of that is simulated in another part. The electrochemical impedance data is acquired firstly by simulating the equivalent circuit with Z-view software. Then, the simulated data was analyzed to investigate the change tendency of a single parameter, providing a theoretical method for developing customized implantable neural interface with specific electrochemical impedance. © 2022 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization Algorithm of Trajectory Rehabilitation Training Mode for Rehabilitation Robot

Trajectory Optimization Algorithm of Trajectory Rehabilitati...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Cen, Yuhui Yuan, Jianjun Ma, Shugen Luo, Jingjing Wang, Hongbo Human Phenome Institute Fudan University Shanghai200438 China The Shanghai Robotics Institute Shanghai University 99 Shangda RD Baoshan District Shanghai China The Department of Robotics Faculty of Science and Engineering Ritsumeikan University 1-1-1 Nojihigashi Shiga Kusatsu Japan Institute of AI and Robotics Academy for Engineering and Technology Fudan University Engineering Research Center of AI & Robotics Ministry of Education Shanghai210043 China

ISBN: (纸本)9781665481090

It is a challenge for robot-assisted rehabilitation therapy to develop a training program with both customized and optimized characteristics. To optimize the scheme of the trajectory rehabilitation training mode, we design a trajectory optimization algorithm with an intelligent decision mechanism. A trajectory smoothing improvement algorithm is proposed to make the trajectory more suitable for rehabilitation training. In addition, we propose an improved genetic algorithm that reduces the optimization time and obtains a better solution. An adaptive variable time weight improved trapezoidal velocity algorithm is innovatively designed by fusing the above two algorithms with an optimal rehabilitation training program as a guide. Based on the experimental platform of the upper limb rehabilitation robot, it is demonstrated that the algorithm can provide comfortable and high-quality rehabilitation training for patients by adaptively optimizing the parameters of the trajectory model according to the training constraints. By combining an intelligent optimization algorithm with a rehabilitation robot trajectory planning algorithm, this paper realizes the unification of customization and optimization of a trajectory rehabilitation training program. © 2022 IEEE.

关键词： Trajectories

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：