检索结果-内蒙古大学图书馆

Toward multi-target self-organizing pursuit in a partially observable Markov game

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Lijun Chang, Yu-Cheng Lyu, Chao Shi, Ye Shi, Yuhui Lin, Chin-Teng Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology China Centre for Artificial Intelligence CIBCI Lab Faculty of Engineering and Information Technology University of Technology Sydney Australia College of Computer and Information Science Southwest University China School of Information Science and Technology ShanghaiTech University China

The multiple-target self-organizing pursuit (SOP) problem has wide applications and has been considered a challenging self-organization game for distributed systems, in which intelligent agents cooperatively pursue multiple dynamic targets with partial observations. This work proposes a framework for decentralized multi-agent systems to improve the implicit coordination capabilities in search and pursuit. We model a self-organizing system as a partially observable Markov game (POMG) featured by large-scale, decentralization, partial observation, and noncommunication. The proposed distributed algorithm-fuzzy self-organizing cooperative coevolution (FSC2) is then leveraged to resolve the three challenges in multi-target SOP: distributed self-organizing search (SOS), distributed task allocation, and distributed single-target pursuit. FSC2 includes a coordinated multi-agent deep reinforcement learning (MARL) method that enables homogeneous agents to learn natural SOS patterns. Additionally, we propose a fuzzy-based distributed task allocation method, which locally decomposes multi-target SOP into several single-target pursuit problems. The cooperative coevolution principle is employed to coordinate distributed pursuers for each single-target pursuit problem. Therefore, the uncertainties of inherent partial observation and distributed decision-making in the POMG can be alleviated. The experimental results demonstrate that by decomposing the SOP task, FSC2 achieves superior performance compared with other implicit coordination policies fully trained by general MARL algorithms. The scalability of FSC2 is proved that up to 2048 FSC2 agents perform efficient multi-target SOP with almost 100% capture rates. Empirical analyses and ablation studies verify the interpretability, rationality, and effectiveness of component algorithms in FSC2. Copyright © 2022, The Authors. All rights reserved.

关键词： Intelligent agents

CLDG: Contrastive Learning on Dynamic Graphs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning

Large Language Models as Evolutionary Optimizers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Shengcai Chen, Caishun Qu, Xinghua Tang, Ke Ong, Yew-Soon Centre for Frontier AI Research A*STAR Department of Computer Science and Engineering Southern University of Science and Technology China Centre for Frontier AI Research A*STAR Tianqiao & Chrissy Chen Institute United States Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology China Centre for Frontier AI Research A*STAR School of Computer Science and Engineering Data Science and Artificial Intelligence Research Centre Nanyang Technological University Singapore

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory performance. In this work, we present the first study on large language models (LLMs) as evolutionary combinatorial optimizers. The main advantage is that it requires minimal domain knowledge and human efforts, as well as no additional training of the model. This approach is referred to as LLM-driven EA (LMEA). Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions. Then, LMEA evaluates these new solutions and include them into the population for the next generation. LMEA is equipped with a self-adaptation mechanism that controls the temperature of the LLM. This enables it to balance between exploration and exploitation and prevents the search from getting stuck in local optima. We investigate the power of LMEA on the classical traveling salesman problems (TSPs) widely used in combinatorial optimization research. Notably, the results show that LMEA performs competitively to traditional heuristics in finding high-quality solutions on TSP instances with up to 20 nodes. Additionally, we also study the effectiveness of LLM-driven crossover/mutation and the self-adaptation mechanism in evolutionary search. In summary, our results reveal the great potentials of LLMs as evolutionary optimizers for solving combinatorial problems. We hope our research shall inspire future explorations on LLM-driven EAs for complex optimization challenges. Copyright © 2023, The Authors. All rights reserved.

关键词： Combinatorial optimization

Concurrent TMS-EEG to characterize cortical responses in the motor and prefrontal cortices in Parkinson's disease

学校读者我要写书评

暂无评论

Neurotherapeutics 2025年 e00577页

作者： Zhu, Lin Cai, Min Pei, Zian Shi, Xue Dang, Ge Lan, Xiaoyong Luo, Xiaoguang Che, Xianwei Guo, Yi Department of Neurology Shenzhen People's Hospital (The Second Clinical Medical College Jinan University The First Affiliated Hospital Southern University of Science and Technology) Guangdong Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Shenzhen Bay Laboratory Guangdong Shenzhen China Centre for Cognition and Brain Disorders The Affiliated Hospital of Hangzhou Normal University Hangzhou China Henan Key Laboratory of Neurorestoratology Henan Joint International Research Laboratory of Neurorestoratology for Senile Dementia Department of Neurology The First Affiliated Hospital of Xinxiang Medical University Xinxiang China

Patients with Parkinson's disease (PD) experience both motor and non-motor symptoms. However, it remains unclear the full spectrum of PD, which requires a comprehensive assessment of both motor and non-motor cortical regions. The use of combined transcranial magnetic stimulation and electroencephalography (TMS-EEG) allows the examination of neural circuit beyond motor cortex. In this study, TMS-EEG data were collected over the primary motor cortex (M1) and dorsolateral prefrontal cortex (DLPFC) in 46 patients with PD and 27 healthy controls (HC). We analyzed TMS-evoked potentials and oscillatory powers to identify differences in cortical excitability and neural connectivity dynamics between the two cohorts. Patients with PD exhibited higher P30 amplitude following M1 stimulation compared to HCs, and there was a positive correlation between P30 amplitude and the severity of motor symptoms. DLPFC stimulation revealed an increased global mean field amplitude area under the curve (GMFA-AUC) at P30 and P60 in the PD group compared to HCs. A significant correlation was also observed within the PD group between P30 and P60 with depression scores. In addition, PD showed a significant power reduction in the alpha and beta bands during stimulation and distinct patterns emerged for each stimulation site. These findings provide novel insights into cortical network abnormalities and contribute to a better understanding of the mechanisms underlying PD. © 2025 The Authors

关键词： Electroencephalography (EEG) Motor and prefrontal cortex Oscillatory responses Parkinson's disease (PD) Transcranial magnetic stimulation (TMS)

DeepNFT: Towards Precise Neurofibrillary Tangle Detection via Improving Multi-scale Feature Fusion and Adversary

学校读者我要写书评

暂无评论

DeepNFT: Towards Precise Neurofibrillary Tangle Detection vi...

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Jiang, Yankai Zhang, Lei Li, Yiming He, Xiangyang Huang, Hanxiao Zhu, Keqing Tao, Yubo Lin, Hai State Key Laboratory of CADCG College of Computer Science and Technology Zhejiang University Hangzhou China Zhejiang University School of Medicine China Brain Bank and Department of Neurology in Second Affiliated Hospital Key Laboratory of Medical Neurobiology of Zhejiang Province Department of Neurobiology Hangzhou China Department of Pathology Zhejiang University School of Medicine Hangzhou China

ISBN: (纸本)9781665401265

Detecting neurofibrillary tangles is an important procedure in the assessment of the intensity and distribution pattern of hippocampal tau pathology, which are the principal clinical phenotypes associated with Alzheimer's disease. Existing deep learning based detectors still face a critical obstacle: the difficulty in detecting extremely small objects in high resolution images. In this paper, we propose a deep learning framework, named DeepNFT, which combines the multilevel feature aggregation pyramid network (MFAPN) and the adversarial feature generation module (AFGM) to acquire precise detection results with significantly reduced false positives. To prove its universality and robustness, DeepNFT has been validated on two datasets. Experiments show the significant performance gain of our proposed approach over state-of-the-art detectors. Ablation study shows our network components improve the performance of various backbones and detectors. © 2021 IEEE.

关键词： Generative adversarial networks

A new knowledge gradient-based method for constrained bayesian optimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Wenjie Liu, Shengcai Tang, Ke Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Black-box problems are common in real life like structural design, drug experiments, and machine learning. When optimizing black-box systems, decision-makers always consider multiple performances and give the final decision by comprehensive evaluations. Motivated by such practical needs, we focus on constrained black-box problems where the objective and constraints lack known special structure, and evaluations are expensive and even with noise. We develop a novel constrained Bayesian optimization approach based on the knowledge gradient method (c − KG). A new acquisition function is proposed to determine the next batch of samples considering optimality and feasibility. An unbiased estimator of the gradient of the new acquisition function is derived to implement the c − KG approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Gradient methods

Dynamical causality under invisible confounders

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Jinling Zhang, Shao-Wu Zhang, Chihao Huang, Weitian Shi, Jifan Chen, Luonan MOE Key Laboratory of Information Fusion Technology School of Automation Northwestern Polytechnical University Xi’an710072 China Key Laboratory of Systems Biology Shanghai Institute of Biochemistry and Cell Biology Center for Excellence in Molecular Cell Science Chinese Academy of Sciences Shanghai200031 China NCMIS CEMS RCSDS Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mathematics Sciences University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Institute of Intelligence Science and Technology Hengqin Guangdong Zhuhai519031 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China State Key Laboratory of Medical Neurobiology MOE Frontiers Center for Brain Science Institutes of Brain Science Fudan University Shanghai200032 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Chinese Academy of Sciences Hangzhou310024 China

Causality inference is prone to spurious causal interactions, due to the substantial confounders in a complex system. While many existing methods based on the statistical methods or dynamical methods attempt to address misidentification challenges, there remains a notable lack of effective methods to infer causality, in particular in the presence of invisible/unobservable confounders. As a result, accurately inferring causation with invisible confounders remains a largely unexplored and outstanding issue in data science and AI fields. In this work, we propose a method to overcome such challenges to infer dynamical causality under invisible confounders (CIC method) and further reconstruct the invisible confounders from time-series data by developing an orthogonal decomposition theorem in a delay embedding space. The core of our CIC method lies in its ability to decompose the observed variables not in their original space but in their delay embedding space into the common and private subspaces respectively, thereby quantifying causality between those variables both theoretically and computationally. This theoretical foundation ensures the causal detection for any high-dimensional system even with only two observed variables under many invisible confounders, which is actually a long-standing problem in the field. In addition to the invisible confounder problem, such a decomposition actually makes the intertwined variables separable in the embedding space, thus also solving the non-separability problem of causal inference. Extensive validation of the CIC method is carried out using various real datasets, and the experimental results demonstrates its effectiveness to reconstruct real biological networks even with unobserved confounders. © 2024, CC BY-NC-ND.

关键词： Time series

Manipulating Piezoelectric and Electro-Strain Properties of BiFeO3-BaTiO3-Based Ceramics Through Chemical Doping-Controlled Domain-Size Engineering

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Lin, Jiamin Liu, Bing Liu, Mengxiang Yang, Shan Zhou, Linming Hong, Zijian Zhu, Xiaoli Wu, Yongjun Li, Juan Huang, Yuhui School of Materials Science and Engineering State Key Laboratory of Silicon and Advanced Semiconductor Materials Cyrus Tang Center for Sensor Materials and Applications Institute of Fundamental and Transdisciplinary Research Zhejiang University Hangzhou310027 China Nanhu Brain-computer Interface Institute Zhejiang Hangzhou311100 China College of Electronic Information and Engineering Hangzhou Dianzi University Zhejiang Hangzhou310018 China Zhejiang Key Laboratory of Advanced Solid State Energy Storage Technology and Applications Taizhou Institute of Zhejiang University Zhejiang Taizhou318000 China School of Engineering Hangzhou City University Zhejiang Hangzhou310015 China College of Materials and Science Engineering Zhejiang University of Technology Zhejiang Hangzhou310006 China

Ferroelectric domains are crucial for the performance of piezoelectric ceramics, as the size and switching dynamics affect polarization response directly, manipulating both ferroelectric and piezoelectric properties. In this study, we achieved BiFeO3-BaTiO3 ceramics with domain sizes from macroscopic to nanoscale by incorporating a small amount of antiferroelectric phase. Contrary to the long-standing belief that smaller ferroelectric domains own lower polarization switching barriers and yield higher piezoelectricity, we found that in chemical doping-controlled domain size engineering, the smaller the domain size, the more difficult it is for polarization switching. Ceramics with the largest domain exhibited superior positive piezoelectric performance due to the sufficient polarization switching and reduced domain wall pinning, achieving a piezoelectric coefficient (d33) of 460 pC/N at 350°C. Middle-sized domains achieved optimal electro-strain performance determined by the trade-off between the domain walls pinning and the increased local tetragonal or orthorhombic symmetries, with a strain (0.29%) and an excellent piezoelectric strain coefficient (d33*) of 726.4 pm/V at 160°C. This work provides novel insights into how domain-size engineering affects domain switching and local distortion, offering guidance for performance optimization of piezoelectric ceramics. © 2025, The Authors. All rights reserved.

关键词： Piezoelectricity

A Generic Fundus Image Enhancement Network Boosted by Frequency Self-supervised Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Heng Liu, Haofeng Fu, Huazhu Xu, Yanwu Shu, Hai Niu, Ke Hu, Yan Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Singapore School of Future Technology South China University of Technology Guangzhou China Pazhou Lab Guangzhou China Department of Biostatistics School of Global Public Health New York University New YorkNY United States Computer School Beijing Information Science and Technology University Beijing China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Fundus photography is prone to suffer from image quality degradation that impacts clinical examination performed by ophthalmologists or intelligent systems. Though enhancement algorithms have been developed to promote fundus observation on degraded images, high data demands and limited applicability hinder their clinical deployment. To circumvent this bottleneck, a generic fundus image enhancement network (GFE-Net) is developed in this study to robustly correct unknown fundus images without supervised or extra data. Levering image frequency information, self-supervised representation learning is conducted to learn robust structure-aware representations from degraded images. Then with a seamless architecture that couples representation learning and image enhancement, GFE-Net can accurately correct fundus images and meanwhile preserve retinal structures. Comprehensive experiments are implemented to demonstrate the effectiveness and advantages of GFE-Net. Compared with state-of-the-art algorithms, GFE-Net achieves superior performance in data dependency, enhancement performance, deployment efficiency, and scale generalizability. Follow-up fundus image analysis is also facilitated by GFE-Net, whose modules are respectively verified to be effective for image enhancement. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement