检索结果-南通市图书馆

Sequential Propagation of Chaos for Mean-Field BSDE Systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Annals of Mathematics,Series B 2024年第1期45卷 11-40页

作者： Xiaochen LI Kai DU shanghai Center for Mathematical Sciences Fudan UniversityShanghai 200433China. shanghai artificial intelligence laboratory 701 Yunjin RoadShanghai 200433China

A new class of backward particle systems with sequential interaction is proposed to approximate the mean-field backward stochastic differential equations.It is proven that the weighted empirical measure of this particle system converges to the law of the McKean-Vlasov system as the number of particles grows.Based on the Wasserstein met-ric,quantitative propagation of chaos results are obtained for both linear and quadratic growth conditions.Finally,numerical experiments are conducted to validate our theoretical results.

关键词： Backward propagation of chaos Particle system Sequential interaction McKean-Vlasov BSDE Convergence rate

Emergence of machine language: towards symbolic intelligence with neural networks

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第4期11卷 27-30页

作者： Yuqi Wang Xu-Yao Zhang Cheng-Lin Liu Tieniu Tan Zhaoxiang Zhang State Key laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of Sciences

Representation learning is a core issue in artificial intelligence (AI). Currently,there exists a disparity in the choice of representation between humans and machines. Humans rely on discrete language for communicati...

关键词：

Orbital angular momentum-mediated machine learning for high-accuracy mode-feature encoding

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第3期13卷 466-477页

作者： Xinyuan Fang Xiaonan Hu Baoli Li Hang Su Ke Cheng Haitao Luan Min Gu Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for artificial-intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Machine learning with optical neural networks has featured unique advantages of the information processing including high speed,ultrawide bandwidths and low energy consumption because the optical dimensions(time,space,wavelength,and polarization)could be utilized to increase the degree of freedom.However,due to the lack of the capability to extract the information features in the orbital angular momentum(OAM)domain,the theoretically unlimited OAM states have never been exploited to represent the signal of the input/output nodes in the neural network model.Here,we demonstrate OAM-mediated machine learning with an all-optical convolutional neural network(CNN)based on Laguerre-Gaussian(LG)beam modes with diverse diffraction losses.The proposed CNN architecture is composed of a trainable OAM mode-dispersion impulse as a convolutional kernel for feature extraction,and deep-learning diffractive layers as a classifier.The resultant OAM mode-dispersion selectivity can be applied in information mode-feature encoding,leading to an accuracy as high as 97.2%for MNIST database through detecting the energy weighting coefficients of the encoded OAM modes,as well as a resistance to eavesdropping in point-to-point free-space transmission.Moreover,through extending the target encoded modes into multiplexed OAM states,we realize all-optical dimension reduction for anomaly detection with an accuracy of 85%.Our work provides a deep insight to the mechanism of machine learning with spatial modes basis,which can be further utilized to improve the performances of various machine-vision tasks by constructing the unsupervised learning-based auto-encoder.

关键词： polarization mode momentum

Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 164-180页

作者： Zongyi XU Xiaoshui HUANG Bo YUAN Yangfu WANG Qianni ZHANG Weisheng LI Xinbo GAO School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Institute for Brain and intelligence Guangyang Bay Laboratory 3. Shanghai Artificial Intelligence Laboratory School of Electronic Engineering and Computer Science Queen Mary University of London

Current methods for point cloud semantic segmentation depend on the extraction of descriptive features. However, unlike images, point clouds are irregular and often lack texture information, making it demanding to extract discriminative features. In addition, noise, outliers, and uneven point distribution are commonly present in point clouds, which further complicates the segmentation task. To address these problems, a novel architecture is proposed for direct and accurate large-scale point cloud segmentation based on point cloud retrieval and alignment. The proposed approach involves using a feature-based point cloud retrieval method for searching for reference point clouds with annotations from a dataset. In the following segmentation stage, an overlap-based point cloud registration method has been developed to align the target and reference point clouds. For accurate and robust alignment, an overlap region estimation module is trained to locate the optimal overlap region between two pieces of point clouds in a coarse-to-fine manner. In the detected overlap region, the global and local features of the points are extracted and combined for featuremetric registration to obtain accurate transformation parameters between the target and reference point clouds. After alignment, the annotated segmentation of the reference is transferred to the target point clouds to obtain accurate segmentation results. Extensive experiments are conducted to show that the developed method outperforms the state-of-the-art approaches in terms of both accuracy and robustness against noise and outliers.

关键词： point cloud semantic segmentation large-scale indoor point clouds point cloud alignment overlap estimation label transfer

Photocatalytic vinyl radical-mediated multicomponent 1,4-/1,8-carboimination across alkynes and olefins/(hetero)arenes

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China Chemistry 2024年第2期67卷 558-567页

作者： Shan-Shan Li Yu-Shi Jiang Xue-Ling Luo Xuming Ran Yuqiang Li Dong Wu Cheng-Xue Pan Peng-Ju Xia School of Chemistry and Pharmaceutical Sciences Guangxi Normal UniversityGuilin541004China shanghai artificial intelligence laboratory Shanghai200433China The Institute for Advanced Studies Wuhan UniversityWuhan430064China

We developed a highly selective and efficient multicomponent transformation by utilizing alkynes and olefins/(hetero)arenes through photoinduced energy-transfer catalysis.The reaction involves the formation of three distinct chemical bonds,namely C(sp~3)–C(sp~2),C(sp~2)–C(sp~3),and C(sp~3)–N,in a single coordinated manner.The strategy used a vinyl radical-mediated radical relay approach under mild conditions,exhibiting a broad substrate scope(>70 examples),excellent functional-group tolerance,and remarkable regio-and anti-stereoselectivity.Through the utilization of a combination of experimental techniques and density functional theory(DFT),we delved deeper into the mechanistic intricacies of this distinctive system.Results revealed that the selective radical addition to electron-deficient alkynes,rather than olefins,was governed by the inherent reactivity of alkyl radicals.This discovery presented a highly effective approach for the synthesis of stereodefined multisubstituted alkenes.

关键词： alkyne-olefin coupling DFT studies regio-and anti-stereoselectivity multisubstituted alkenes

Tipping Point Detection Using Reservoir Computing

在线全文

学校读者我要写书评

暂无评论

Research 2024年第1期6卷 779-790页

作者： Xin Li Qunxi Zhu Chengli Zhao Xuzhe Qian Xue Zhang Xiaojun Duan Wei Lin College of Science National University of Defense TechnologyChangshaHunan 410073China Research Institute of Intelligent Complex Systems and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China shanghai artificial intelligence laboratory Shanghai 200232China School of Mathematical Sciences SCMSSCAMand CCSBFudan UniversityShanghai 200433China

Detection in high fidelity of tipping points,the emergence of which is often induced by invisible changes in internal structures or/and external interferences,is paramountly beneficial to understanding and predicting complex dynamical systems(CDSs).Detection approaches,which have been fruitfully developed from several perspectives(e.g.,statistics,dynamics,and machine learning),have their own advantages but still encounter difficulties in the face of high-dimensional,fluctuating datasets.Here,using the reservoir computing(RC),a recently notable,resource-conserving machine learning method for reconstructing and predicting CDSs,we articulate a model-free framework to accomplish the detection only using the time series observationally recorded from the underlying unknown CDSs.

关键词： computing record ping

A Bio-Inspired Integration Model of Basal Ganglia and Cerebellum for Motion Learning of a Musculoskeletal Robot

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第1期37卷 82-113页

作者： ZHANG Jinhan CHEN Jiahao ZHONG Shanlin QIAO Hong State Key laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China.

It is a significant research direction for highly complex musculoskeletal robots that how to develop the ability of motion learning and generalization.The cooperations of multiple brain regions are crucial to improving motion performance.Inspired by the neural mechanisms of structures,functions,and interconnections of basal ganglia and cerebellum,a biologically inspired integration model for motor learning of musculoskeletal robots is proposed.Based on the neural characteristics of the basal ganglia,the basal ganglia actor network,which mainly simulates the dorsal striatum,outputs motion commands,and the basal ganglia critic network,which simulates the ventral striatum,estimates actionstate values.Their network parameters are updated using the soft actor-critic method.Based on the sensorimotor prediction mechanism of the cerebellum,the cerebellum network evaluates the state feature extraction quality of the basal ganglia actor network and then updates the weights of its feature layer.This learning method is proven to converge to the optimal policy.Furthermore,drawing on the mechanism of dopaminergic dynamic regulation in the basal ganglia,the adaptive adjustment of target entropy and the dopaminergic experience replay are proposed to further improve the integration model,which contributes to the exploration-exploitation trade-off of motor learning.The bio-inspired integration model is validated on a musculoskeletal system.Experimental results indicate that this model can effectively control the musculoskeletal robot to accomplish the motion task from random starting locations to random target positions with high precision and robustness.

关键词： Basal ganglia and cerebellum bio-inspired integration model motion learning musculoskeletal robot reinforcement learning.

Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 549-562页

作者： Supeng Yu Fen Huang Chengcheng Fan College of artificial intelligence Nanjing Agricultural UniversityNanjing210095China Innovation Academy for Microsatellites of CAS Shanghai201210China shanghai Engineering Center for Microsatellites Shanghai201210China Key laboratory of Satellite Digital Technology Shanghai201210China

Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.

关键词： Semantic segmentation road extraction weakly supervised learning scribble supervision remote sensing image

Ultrahigh performance passive radiative cooling by hybrid polar dielectric metasurface thermal emitters

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Opto-Electronic Advances 2024年第4期7卷 17-25页

作者： Yinan Zhang Yinggang Chen Tong Wang Qian Zhu Min Gu Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for artificial-intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China

Real-world passive radiative cooling requires highly emissive,selective,and omnidirectional thermal emitters to maintain the radiative cooler at a certain temperature below the ambient temperature while maximizing the net cooling power.Despite various selective thermal emitters have been demonstrated,it is still challenging to achieve these conditions sim-ultaneously because of the extreme difficulty in controlling thermal emission of photonic structures in multidimension.Here we demonstrated hybrid polar dielectric metasurface thermal emitters with machine learning inverse design,en-abling a high emissivity of~0.92 within the atmospheric transparency window 8-13μm,a large spectral selectivity of~1.8 and a wide emission angle up to 80 degrees,simultaneously.This selective and omnidirectional thermal emitter has led to a new record of temperature reduction as large as~15.4°C under strong solar irradiation of~800 W/m2,signific-antly surpassing the state-of-the-art results.The designed structures also show great potential in tackling the urban heat island effect,with modelling results suggesting a large energy saving and deployment area reduction.This research will make significant impact on passive radiative cooling,thermal energy photonics and tackling global climate change.

关键词： radiative cooling dielectric metasurfaces machine learning thermal emitters