检索结果-内蒙古大学图书馆

Raven solver: From perception to reasoning

INFORMATION SCIENCES 2023年 634卷 716-729页

作者： Wei, Qinglai Chen, Diancheng Yuan, Beiming Ye, Peijun Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China

A higher level of machine intelligence is expected after the prosperity of deep learning in computer vision. The Raven's progressive matrices (RPM), for example, raises the requirements of learning from perception to reasoning. Previous solutions for RPM tend to build monolithic end -to-end models, whose excellent performances are of no comfort given that their interpretability and generalizability are far from satisfactory. With hindsight, we formalize RPM as a stratified problem, and propose an eclectic solver. To recapitulate, we explore the possibility of deep contrastive learning for interpretable feature extraction, deep regression with rule representation, and information pooling for reasoning and generalization. Our model achieves 94.63% and 92.90% in RAVEN and I-RAVEN datasets, and demonstrates interpretability in visual attribute learning. More than that, we also discover one potential defect of the original RAVEN dataset.

关键词： Deep learning Raven?s progressive matrices Abstract reasoning Contrastive learning Model interpretability

来源：评论

学校读者我要写书评

暂无评论

Policy generation network for zero-shot policy learning

引用

COMPUTATIONAL INTELLIGENCE 2023年第5期39卷 707-733页

作者： Qian, Yiming Zhang, Fengyi Liu, Zhiyong Univ Chinese Acad Sci UCAS Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Chinese Acad Sci Cloud Comp Ctr Dongguan Guangdong Peoples R China

Lifelong reinforcement learning is able to continually accumulate shared knowledge by estimating the inter-task relationships based on training data for the learned tasks in order to accelerate learning for new tasks by knowledge reuse. The existing methods employ a linear model to represent the inter-task relationships by incorporating task features in order to accomplish a new task without any learning. But these methods may be ineffective for general scenarios, where linear models build inter-task relationships from low-dimensional task features to high-dimensional policy parameters space. Also, the deficiency of calculating errors from objective function may arise in the lifelong reinforcement learning process when some errors of policy parameters restrain others due to inter-parameter correlation. In this paper, we develop a policy generation network that nonlinearly models the inter-task relationships by mapping low-dimensional task features to the high-dimensional policy parameters, in order to represent the shared knowledge more effectively. At the same time, we propose a novel objective function of lifelong reinforcement learning to relieve the deficiency of calculating errors by adding weight constraints for errors. We empirically demonstrate that our method improves the zero-shot policy performance across a variety of dynamical systems.

关键词： knowledge representation lifelong reinforcement learning zero-shot policy generation

来源：评论

学校读者我要写书评

暂无评论

On Intelligent Mining With Parallel Intelligence

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第10期8卷 4296-4300页

作者： Yang, Jianjian Huang, Qiankun Ge, Shirong Wang, Xiao Chen, Long Guo, Yinan Gui, Tianmu China Univ Min & Technol Beijing Sch Mech Elect Engn Beijing 100083 Peoples R China Anhui Univ Hefei 266114 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The level of intelligence across various industries, including mining, has experienced a notable advancement since the introduction of Industry 4.0. However, the societal demands for employee well-being, resource conservation, and environmental preservation continues to be unavoidable challenges. Thus, the parallel system theory based Industry 5.0 is proposed, which augments industries with human-machine collaboration, virtual-real interaction and local-global balanced resources. In this letter, we proposed the concept of Mining 5.0. Mining 5.0 aims to realize green and sustainable development goals while prioritizing a human-centric perspective. This letter begins by elucidating the prerequisites, characteristics, and construction objectives of Mining 5.0. It then introduces the "4I", "5O" and "6S" concluded framework of "Intelligent Mining Using Parallel Intelligence" for achieving Mining 5.0. In the last part, the efforts made by Chinese mining research institutions and leading enterprises in the development of mining intelligence standards, and the practical application of parallel mining within the mining sector are outlined. This letter is a summary of recent Distributed/Decentralized Hybrid Workshop on Autonomous Mining (DHW-AM) and aims at enhancing the intelligence of future mining operations.

关键词： Data mining Artificial intelligence Task analysis Industries Production Biology Collaboration Green mining Industry 5.0 intelligent mining using parallel intelligence Mining 5.0 mining MAPeM model

来源：评论

学校读者我要写书评

暂无评论

Generating Emotion Descriptions for Fine Art Paintings Via Multiple Painting Representations

引用

IEEE INTELLIGENT systems 2023年第3期38卷 31-40页

作者： Lu, Yue Guo, Chao Dai, Xingyuan Wang, Fei-Yue Chinese Acad Sci Inst Automation State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Inst Sci & Art Natl Museum China Beijing 100006 Peoples R China

The task of generating emotion descriptions for fine art paintings using machine learning is gaining increasing attention. However, captioning the emotions depicted in paintings is challenging due to the artistic and subtle nature of the relied-upon visual clues. Previous studies on painting emotion captioning mainly focus on content-oriented semantic features, resulting in limited performance. Recognizing that facial expressions and body language can reflect human emotions, we propose a novel painting emotion captioning model that incorporates two additional features: facial expression feature and human pose feature. Our model includes a feature fusion method to incorporate these features with commonly used object features. The experiment results on public datasets demonstrate that our proposed model outperforms the baseline. Further experiments on paintings with abstract appearances and image corruptions show the promising performance of our proposed model.

关键词： Painting Feature extraction Emotion recognition Detectors Intelligent systems Convolutional neural networks Art

来源：评论

学校读者我要写书评

暂无评论

Scale-Disentangled and Uncertainty-Guided Alignment for Domain-Adaptive Object Detection

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2024年第12期25卷 19507-19521页

作者： Zhang, Hui Luo, Guiyang Cao, Yuanzhouhan Wang, Xiao Li, Yidong Wang, Fei-Yue Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Beijing Jiaotong Univ Key Lab Big Data & Artificial Intelligence Transp Minist Educ Beijing 100044 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Minist Educ Engn Res Ctr Autonomous Unmanned Syst Technol Hefei 230601 Anhui Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Unsupervised domain adaptive object detection methods aim to transfer knowledge from the label-sufficient domain to the unlabeled domain. Most existing works minimize domain disparity by concentrating on different levels through adversarial learning. However, adversarial learning do not consider the different influences on under-aligned and well-aligned samples as they merely match distinct distributions with consistent weight. To address this issue, we design a novel scale-disentangled and uncertainty-guided alignment for domain-adaptive object detection (SDUGA), consisting of three main components: (1) Disentangled scale coarse module, which decouples scale information from global image features and performs individual alignment across domains for the corresponding scale by training domain classifiers in an adversarial learning manner;(2) Disentangled scale fine module, which generalizes the disentangled scale alignment to instance-level adaptation, reinforcing the distribution alignment across domains from multi-scale local instance level;(3) Uncertainty-guided coarse-to-fine attention alignment, which adjusts weights for various samples adaptively by generating the uncertainty-guided attention map, thus enforcing the detector to converge more on alignment for under-aligned samples and avoid misaligning well-aligned ones. Extensive experiments over three challenging domain-shift object detection scenarios demonstrate that SDUGA gains superior performance compared to state-of-the-art methods.

关键词： Object detection domain adaptation deep learning adversarial feature learning

来源：评论

学校读者我要写书评

暂无评论

Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter

引用

ROBOTICA 2023年第2期41卷 470-485页

作者： Lu, Ning Cai, Yinghao Lu, Tao Cao, Xiaoge Guo, Weiyan Wang, Shuo China Waterborne Transport Res Inst Beijing 100088 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Ctr Excellence Brain Sci & Intelligence Technol Shanghai 200031 Peoples R China

"Picking out the impurities" is a typical scenario in production line which is both time consuming and laborious. In this article, we propose a target-oriented robotic push-grasping system which is able to actively discover and pick the impurities in dense environments with the synergies between pushing and grasping actions. First, we propose an attention module, which includes target saliency detection and density-based occluded-region inference. Without the necessity of expensive labeling of semantic segmentation, our attention module can quickly locate the targets in the view or predict the candidate regions where the targets are most likely to be occluded. Second, we propose a push-grasp synergy framework to sequentially select proper actions in different situations until all targets are picked out. Moreover, we introduce an active pushing mechanism based on a novel metric, namely Target-Centric Dispersion Degree (TCDD) for better grasping. TCDD describes whether the targets are isolated from the surrounding objects. With this metric, the robot becomes more focused on the actions around the targets and push irrelevant objects away. Experimental results on both simulated environment and real-world environment show that our proposed system outperforms several baseline approaches,which also has the capability to be generalized to new scenarios.

关键词： saliency Detection robot Learning push-grasp target-oriented Grasping deep Q Network

来源：评论

学校读者我要写书评

暂无评论

ABCP: Automatic Blockwise and Channelwise Network Pruning via Joint Search

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2023年第3期15卷 1560-1573页

作者： Li, Jiaqi Li, Haoran Chen, Yaran Ding, Zixiang Li, Nannan Ma, Mingjun Duan, Zicheng Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, for simple tasks like robotic detection, most of the traditional rule-based network pruning methods cannot reach a sufficient compression ratio with low accuracy loss and are time consuming as well as laborious. In this article, we propose automatic blockwise and channel-wise network pruning (ABCP) to jointly search the blockwise and channelwise pruning action for robotic detection by deep reinforcement learning. A joint sample algorithm is proposed to simultaneously generate the pruning choice of each residual block and the channel pruning ratio of each convolutional layer from the discrete and continuous search space, respectively. The best pruning action taking both the accuracy and the complexity of the model into account is obtained finally. Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss. Tested on the mobile robot detection data set, the pruned YOLOv3 model saves 99.5% floating-point operations, reduces 99.5% parameters, and achieves 37.3x speed up with only 2.8% mean of average precision (mAP) loss. On the sim2real detection data set for robotic detection task, the pruned YOLOv3 model achieves 9.6% better mAP than the baseline model, showing better robustness performance.

关键词： Joint search model compression pruning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automated Silicon-Substrate Ultra-Microtome for Automating the Collection of Brain Sections in Array Tomography

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 389-401页

作者： Long Cheng Weizhou Liu Chao Zhou Yongxiang Zou Zeng-Guang Hou the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Understanding the structure and working principle of brain neural networks requires three-dimensional reconstruction of brain tissue samples using array tomography *** order to improve the reconstruction performance,the sequence of brain sections should be collected with silicon wafers for subsequent electron microscopic ***,the current collection of brain sections based on silicon substrate involve mainly manual collection,which requires the involvement of automation techniques to increase collection *** paper presents the design of an automatic collection device for brain ***,a novel mechanism based on circular silicon substrates is proposed for collection of brain sections;second,an automatic collection system based on microscopic object detection and feedback control strategy is *** results verify the function of the proposed collection *** objects(brain section,left baffle,right baffle)can be detected from microscopic images by the proposed detection *** efficiency can be further improved with position feedback of brain sections *** has been experimentally verified that the proposed device can well fulfill the task of automatic collection of brain *** the help of the proposed automatic collection device,human operators can be partially liberated from the tedious manual collection process and collection efficiency can be improved.

关键词： Array tomography automatic collection system brain sections microscopic object detection serial section

来源：评论

学校读者我要写书评

暂无评论

Traffic Forecasting via Dilated Temporal Convolution With Peak-Sensitive Loss

引用

IEEE INTELLIGENT TRANSPORTATION systems MAGAZINE 2023年第1期15卷 48-57页

作者： Guo, Ge Yuan, Wei Liu, Jinyuan Lv, Yisheng Liu, Wei Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Northeastern Univ Res Acad Shenyang Peoples R China Neusoft Corp Intelligent Vis Lab Shenyang 110819 Peoples R China

Deep learning-based traffic forecasting methods can capture intricate spatiotemporal features in traffic data and environmental factors. However, they have unsatisfactory performance around the minority peaks and are inefficient for modeling wide-range spatial correlations. This article gives a peak-aware deep learning architecture for traffic forecasting by involving a cost-sensitive loss function called peak-sensitive loss. This method can improve the performance since different costs are employed on the prevalent metrics such as mean-square loss and square of mean absolute percentage loss. A spatiotemporal convolutional architecture based on a dilated convolutional network (DCN) and a temporal convolutional network (TCN) is constructed that models the spatial features (both wide and short range) by the DCN and learns the time characteristics by the TCN. The effectiveness of the model is demonstrated with real-world data sets.

关键词： Correlation Spatiotemporal phenomena Forecasting Data models Deep learning Convolution Predictive models

来源：评论

学校读者我要写书评

暂无评论

Parallel Driving with Big Models and Foundation Intelligence in Cyber-hysical-ocial Spaces

引用

Research 2024年第2期2024卷 1-17页

作者： Xiao Wang Jun Huang Yonglin Tian Chen Sun Lie Yang Shanhe Lou Chen Lv Changyin Sun Fei-Yue Wang School of Artificial Intelligence Anhui UniversityHefeiChina Macao University of Science and Technology MacaoChina State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina MVSLab Department of Mechanical and Mechatronics EngineeringUniversity of Waterloo200 University Ave WestWaterlooON N2L3G1Canada School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingaporeSingapore

Recent years have witnessed numerous technical breakthroughs in connected and autonomous vehicles (CAVs). On the one hand, these breakthroughs have significantly advanced the development of intelligent transportation systems (ITSs);on the other hand, these new traffic participants introduce more complex and uncertain elements to ITSs from the social space. Digital twins (DTs) provide real-time, data-driven, precise modeling for constructing the digital mapping of physical-world ITSs. Meanwhile, the metaverse integrates emerging technologies such as virtual reality/mixed reality, artificial intelligence, and DTs to model and explore how to realize improved sustainability, increased efficiency, and enhanced safety. More recently, as a leading effort toward general artificial intelligence, the concept of foundation model was proposed and has achieved significant success, showing great potential to lay the cornerstone for diverse artificial intelligence applications across different domains. In this article, we explore the big models embodied foundation intelligence for parallel driving in cyber-physical-social spaces, which integrate metaverse and DTs to construct a parallel training space for CAVs, and present a comprehensive elucidation of the crucial characteristics and operational mechanisms. Beyond providing the infrastructure and foundation intelligence of big models for parallel driving, this article also discusses future trends and potential research directions, and the ?S?goals of parallel driving.

关键词： breakthrough integrate corners

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：