检索结果-内蒙古大学图书馆

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

作者： Zhou, Jinfeng Wang, Bo Huang, Minlie Zhao, Dongming Huang, Kun He, Ruifang Hou, Yuexian College of Intelligence and Computing Tianjin University Tianjin China State Key Laboratory of Communication Content Cognition People's Daily Online Beijing China The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China AI Lab China Mobile Communication Group Tianjin Co. Ltd. China

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations. However, existing conversational recommendation systems (CRS) ignore the advantage of user interest shift in connecting recommendation and conversation, which leads to an ineffective loose coupling structure of CRS. To address this issue, by modeling the recommendation actions as recommendation paths in a knowledge graph (KG), we propose DICR (Dual Imitation for Conversational Recommendation), which designs a dual imitation to explicitly align the recommendation paths and user interest shift paths in a recommendation module and a conversation module, respectively. By exchanging alignment signals, DICR achieves bidirectional promotion between recommendation and conversation modules and generates high-quality responses with accurate recommendations and coherent explanations. Experiments demonstrate that DICR outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics. © 2022 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Decentralized Adaptive Critic Control Design for a Class of Disturbed Nonlinear Interconnected systems

Decentralized Adaptive Critic Control Design for a Class of ...

引用

第34届中国控制与决策会议

作者： Wenqian Fan Ding Wang Menghua Li Jin Ren Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing Laboratory of Smart Environmental Protection Beijing University of Technology

In this paper,we establish a neural-network-based adaptive dynamic programming(ADP) method to address the decentralized control problem for nonlinear continuous-time(CT) interconnected systems with external ***,the optimal control schemes of the isolated subsystems are constructed,which are based on the appropriate cost ***,it is accessible to establish the effective decentralized control strategy of the large-scale systems by adding suitable feedback ***,by taking into account the disturbance rejection issue,the Hamilton-Jacobi-Isaacs(HJI) equation can be *** solve the HJI equation,a series of critic neural networks are developed to obtain the cost functions and the optimal control strategies ***,a novel weight updating rule is proposed during the neural critic learning ***,the simulation results are presented to display the decentralized control performance by adopting the neural-network-based ADP method.

关键词： Adaptive dynamic programming Decentralized control Disturbance rejection Neural networks Nonlinear interconnected systems Optimal control

来源：评论

学校读者我要写书评

暂无评论

Decoupling Learning and Remembering: a Bilevel Memory Framework with Knowledge Projection for Task-Incremental Learning

Decoupling Learning and Remembering: a Bilevel Memory Framew...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wenju Sun Qingyong Li Jing Zhang Wen Wang Yangli-Ao Geng Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University

The dilemma between plasticity and stability arises as a common challenge for incremental learning. In contrast, the human memory system is able to remedy this dilemma owing to its multilevel memory structure, which motivates us to propose a Bilevel Memory system with Knowledge Projection (BMKP) for incremental learning. BMKP decouples the functions of learning and remembering via a bilevel-memory design: a working memory responsible for adaptively model learning, to ensure plasticity; a long-term memory in charge of enduringly storing the knowledge incorporated within the learned model, to guarantee stability. However, an emerging issue is how to extract the learned knowledge from the working memory and assimilate it into the long-term memory. To approach this issue, we reveal that the parameters learned by the working memory are actually residing in a redundant high-dimensional space, and the knowledge incorporated in the model can have a quite compact representation under a group of pattern basis shared by all incremental learning tasks. Therefore, we propose a knowledge projection process to adaptively maintain the shared basis, with which the loosely organized model knowledge of working memory is projected into the compact representation to be remembered in the long-term memory. We evaluate BMKP on CIFAR-10, CIFAR-100, and Tiny-ImageNet. The experimental results show that BMKP achieves state-of-the-art performance with lower memory usage 1 1 The code is available at https://***/SunWenJu123/BMKP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Inter-Layer Volumetric Attention Network for Teeth Segmentation in Cross-FOV CBCT Dental Images

An Inter-Layer Volumetric Attention Network for Teeth Segmen...

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Fan Qin Xiaoguang Li Muqing Liu Zhiwei Huang Jianhui Han Li Zhuo School of Information Science Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China Department of Oral & Maxillofacial Radiology Peking University School & Hospital of Stomatology Beijing China Department of Oral and Maxillofacial Radiology School of Stomatology Capital Medical University Beijing China

ISBN: (数字)9798350363203

ISBN: (纸本)9798350363210

Accurate teeth segmentation is the foundation of intelligent analysis in dental CBCT images and has significant application value for oral clinical practice. The existing teeth segmentation algorithms mainly focus on the oral image with a global field of view. However, in clinical data, CBCT oral data has significant differences in the field of views. This paper proposes a cross-view oral CBCT teeth segmentation network based on an inter-layer volumetric attention network to address the challenges of different perspectives. Firstly, a 3D inter-layer cross-attention mechanism was designed to handle different visual field features effectively. Secondly, a target scale normalization strategy based on physical resolution is introduced to align teeth in various field of views. Finally, a local random cropping training strategy is adopted to improve the robustness of the teeth segmentation network. In addition, this paper also excludes areas unrelated to teeth through ROI detection. The experimental results show that the proposed method achieves robust and accurate cross-field segmentation in clinical CBCT oral images.

关键词： Training Location awareness Image segmentation Visualization Accuracy Attention mechanisms Three-dimensional displays Teeth Robustness Dentistry

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Dynamic Error Compensation in 3D Printing

Deep Reinforcement Learning for Dynamic Error Compensation i...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Dong Wang Zhen Shen Xiangyang Dong Qihang Fang Weixing Wang Xisong Dong Gang Xiong School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

In the 3D printing process, various error factors can affect the accuracy of the final printing quality. However, current 3D printing error compensation methods have limited effects and usually cannot work in real-time. The 3D printing error compensation process is modeled as a Markov decision process (MDP) in this paper, and Deep Reinforcement Learning (DRL) is applied for dynamic error compensation. This method learns autonomously through trial and error by interacting with the printing environment, which makes it adaptable to various types of 3D printers without specific training. Then, we simulate the digital light processing (DLP) 3D printing. Due to the huge state and action space of sliced images, applying the DRL algorithm to DLP is challenging. We propose an error compensation method based on morphological image operation and use Autoencoder to extract error features to reduce the state space. We then implement our method using a Twin Delayed Deep Deterministic policy gradient algorithm (TD3). The results demonstrate the effects of our method in compensating 3D printing errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fan flue gas temperature control system based on fuzzy PID control

Fan flue gas temperature control system based on fuzzy PID c...

引用

Data Driven Control and Learning systems (DDCLS)

作者： Zihao Wang Xiaoli Li Kang Wang Yang Li Faculty of Information Technology Beijing University of Technology Beijing Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing Engineering Research Center of Digital Community Beijing University of Technology Beijing School of International Studies Communication University of China(CUC) Beijing

Due to the complex process of flue gas acid production and numerous processes, the controlled objects in the whole process have the characteristics of time-variation, randomness, nonlinearity and large lag. For SO2 fan, because the traditional PID control adopts the parameters set in advance, it is difficult to play an effective role in the complex flue gas acid production system, therefore, a fuzzy PID control method is proposed. The two-dimensional structure fuzzy controller model with two inputs and three outputs can dynamically adjust the PID controller parameters. By establishing a transfer function model for factory temperature data, we compare the fuzzy PID control with the traditional PID controller. The results demonstrate that the fuzzy PID controller possesses strong anti-interference ability, has a shorter adjustment time, and exhibits a smaller overshoot volume, which enables more effective control of the fan outlet temperature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous Monitoring of Tissue Oxygen Metabolism Based on Multi-Wavelength Diffuse Correlation Spectroscopy Using Lstm-Based Rnn Model

SSRN

引用

SSRN 2023年

作者： Li, Zhe Bai, Jiangtao Jiang, Minnan Feng, Jinchao Chen, Xing Wei, Ran Jia, Kebin Beijing University of Technology Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Laboratory of Advanced Information Networks Beijing China Beihang University School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beijing China Beijing College of Social Administration Beijing China

Growing incidences of cardiovascular diseases have driven demand for continuous tissue oxygen metabolism monitoring. Diffuse optical spectroscopy (DOS) or near-infrared spectroscopy (NIRS) is typically employed to measure oxygenated and de-oxygenated hemoglobin, while diffuse correlation spectroscopy (DCS) provides a direct measure of tissue blood flow noninvasively. Traditionally, combined DCS and DOS approaches are utilized for monitoring oxygen metabolism, which result in high time-consuming and data noise drawbacks due to the complex and high-cost system. In this paper, we evaluate the utility of multi-wavelength diffuse correlation spectroscopy (mwDCS) using a proposed deep learning approach, i.e., long short-term memory (LSTM) based recurrent neural network (RNN). Arterial occlusion experiments were performed in vivo to generate the data from 6 healthy individuals. Further, based on the dataset acquired by mwDCS, a LSTM-based RNN model was developed to directly assess changes of blood flow and oxygen saturation. Compared to conventional methods, the in vivo experiments in this study demonstrated a more portable system with promising results. Pearsons correlation coefficients of the proposed model reached 0.82 and 0.64 for the changes of blood flow and oxygen saturation, respectively. Our results shows that mwDCS using LSTM-based RNN model provides an alternative method for continuous tissue oxygen metabolism monitoring. © 2023, The Authors. All rights reserved.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Prediction of HVAC Energy Consumption Using PSO Optimized Deep Neural Network

Prediction of HVAC Energy Consumption Using PSO Optimized De...

引用

Data Driven Control and Learning systems (DDCLS)

作者： Linhui Du Xiaoli Li Kang Wang Yang Li Faculty of Information Technology Beijing University of Technology Beijing Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing Engineering Research Center of Digital Community Beijing University of Technology Beijing School of International Studies Communication University of China(CUC) Beijing

Heating, Ventilation and Air Conditioning (HVAC) system is a highly nonlinear system with a large amount of complex, coupled inputs. This paper presents a novel prediction method for HVAC energy consumption based on deep neural network (DNN). In order to solve the problem that traditional neural networks tend to fall into local optima, batch normalization and Adam optimization algorithm are significantly incorporated in the DNN. In addition, particle swarm optimization (PSO) is utilized to search for the optimal number of hidden layer nodes and increase the accuracy of prediction model. The cooling tower data of HVAC is used to validate the network. The results show the mean absolute error and the mean square error of the PSO-DNN model, from which it can be seen obviously that our proposed prediction model performs better than traditional ones. Accordingly, DNN optimized by PSO algorithm is of great validity and superiorities for energy consumption prediction of HVAC system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MRIN: Fine-grained Feature Interaction based on Multiple Feature Relationships for CTR Prediction

MRIN: Fine-grained Feature Interaction based on Multiple Fea...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jianbang Ju Yingyuan Xiao Peilin Yang Wenguang Zheng Enginnering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China

CTR prediction is an important task in personalized recommendation and online advertising. In recent years, many models have been applied in CTR prediction systems to imporve the predcition accuracy. Although the current work has achieved results, the diversity of relationships between the different features was ignored: 1) most existing models usually use the vector-product to realize the interaction of each feature pairs, which ignore the potential contexts between the different feature interactions and lack the different interactive behaviors between the same pair of features; 2) most existing models usually only consider the importance of features of the same order, which ignore the weight relationships between the different feature *** this paper, we propose a novel deep learning model called Multi-Relational Interaction Network (MRIN), which learns fine-grained feature interactions and captures latent relationships between features. On the one hand, we design two interactive modules that take different interactive methods to learn the feature interactions in the potential contexts. On the other hand, we flexibly apply attention network to further automatically learn the weight relationships between different feature representations. Extensive experiments conducted on two public datasets prove the effectiveness of our proposed model, which has better performance than the state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Audio-visual Learning:A Survey

引用

International Journal of Automation and computing 2021年第3期18卷 351-376页

作者： Hao Zhu Man-Di Luo Rui Wang Ai-Hua Zheng Ran He Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and TechnologyAnhui UniversityHefei 230601China Center for Research on Intelligent Perception and Computing(CRIPAC)and National Laboratory of Pattern Recognition(NLPR) Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of the Chinese Academy of SciencesBeijing 100049China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of SciencesShanghai 200031China

Audio-visual learning,aimed at exploiting the relationship between audio and visual modalities,has drawn considerable attention since deep learning started to be used *** tend to leverage these two modalities to improve the performance of previously considered single-modality tasks or address new challenging *** this paper,we provide a comprehensive survey of recent audio-visual learning *** divide the current audio-visual learning tasks into four different subfields:audiovisual separation and localization,audio-visual correspondence learning,audio-visual generation,and audio-visual representation ***-of-the-art methods,as well as the remaining challenges of each subfield,are further ***,we summarize the commonly used datasets and challenges.

关键词： Deep audio-visual learning audio-visual separation and localization correspondence learning generative models representation 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：