检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on machine Learning

作者： Juntao Dai Yaodong Yang Qian Zheng Gang Pan College of Computer Science and Technology and The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China Center for AI Safety and Governance Peking University Beijing China

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation (ABE) method relies on the infinite-horizon discounted advantage function. This dependence leads to catastrophic errors in finite-horizon scenarios with non-discounted constraints, resulting in safety-violation updates. In response, we propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL, termed Gradient-based Estimation (GBE), which relies on the analytic gradient derived along trajectories. Our theoretical and empirical analyses demonstrate that GBE can effectively estimate constraint changes over a finite horizon. Constructing a surrogate optimization problem with GBE, we developed a novel Safe RL algorithm called Constrained Gradient-based Policy Optimization (CGPO). CGPO identifies feasible optimal policies by iteratively resolving sub-problems within trust regions. Our empirical results reveal that CGPO, unlike baseline algorithms, successfully estimates the constraint functions of subsequent policies, thereby ensuring the efficiency and feasibility of each update.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Alleviating the semantic gap for generalized fMRI-to-image reconstruction 23

Alleviating the semantic gap for generalized fMRI-to-image r...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Tao Fang Qian Zheng Gang Pan College of Computer Science and Technology Zhejiang University Hangzhou China and The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China

Although existing fMRI-to-image reconstruction methods could predict high-quality images, they do not explicitly consider the semantic gap between training and testing data, resulting in reconstruction with unstable and uncertain semantics. This paper addresses the problem of generalized fMRI-to-image reconstruction by explicitly alleviates the semantic gap. Specifically, we leverage the pre-trained CLIP model to map the training data to a compact feature representation, which essentially extends the sparse semantics of training data to dense ones, thus alleviating the semantic gap of the instances nearby known concepts (i.e., inside the training super-classes). Inspired by the robust low-level representation in fMRI data, which could help alleviate the semantic gap for instances that far from the known concepts (i.e., outside the training super-classes), we leverage structural information as a general cue to guide image reconstruction. Further, we quantify the semantic uncertainty based on probability density estimation and achieve Generalized fMRI-to-image reconstruction by adaptively integrating Expanded Semantics and Structural information (GESS) within a diffusion process. Experimental results demonstrate that the proposed GESS model outperforms state-of-the-art methods, and we propose a generalized scenario split strategy to evaluate the advantage of GESS in closing the semantic gap. Our codes are available at https://***/duolala1/GESS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility

arXiv

引用

arXiv 2023年

作者： Feng, Lang Xing, Dong Zhang, Junru Pan, Gang College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China

Existing multi-agent PPO algorithms lack compatibility with different types of parameter sharing when extending the theoretical guarantee of PPO to cooperative multi-agent reinforcement learning (MARL). In this paper, we propose a novel and versatile multi-agent PPO algorithm for cooperative MARL to overcome this limitation. Our approach is achieved upon the proposed full-pipeline paradigm, which establishes multiple parallel optimization pipelines by employing various equivalent decompositions of the advantage function. This procedure successfully formulates the interconnections among agents in a more general manner, i.e., the interconnections among pipelines, making it compatible with diverse types of parameter sharing. We provide a solid theoretical foundation for policy improvement and subsequently develop a practical algorithm called Full-Pipeline PPO (FP3O) by several approximations. Empirical evaluations on MultiAgent MuJoCo and StarCraftII tasks demonstrate that FP3O outperforms other strong baselines and exhibits remarkable versatility across various parameter-sharing configurations. Copyright © 2023, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting 39

EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaus...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Chen, Zehao Lu, Zhan Ma, De Tang, Huajin Jiang, Xudong Zheng, Qian Pan, Gang The State Key Lab of Brain-Machine Intelligence Zhejiang University China College of Computer Science and Technology Zhejiang University China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)157735897X

High Dynamic Range (HDR) video reconstruction seeks to accurately restore the extensive dynamic range present in real-world scenes and is widely employed in downstream applications. Existing methods typically operate on one or a small number of consecutive frames, which often leads to inconsistent brightness across the video due to their limited perspective on the video sequence. Moreover, supervised learning-based approaches are susceptible to data bias, resulting in reduced effectiveness when confronted with test inputs exhibiting a domain gap relative to the training data. To address these limitations, we present an event-guided HDR video reconstruction method through building 3D Gaussian Splatting (3DGS), to ensure consistent brightness imposed by 3D consistency. We introduce HDR 3D Gaussians capable of simultaneously representing HDR and low-dynamic-range (LDR) colors. Furthermore, we incorporate a learnable HDR-to-LDR transformation optimized by input event streams and LDR frames to eliminate the data bias. Experimental results on both synthetic and real-world datasets demonstrate that the proposed method achieves state-of-the-art performance. © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

EvSTVSR: Event Guided Space-Time Video Super-Resolution 39

EvSTVSR: Event Guided Space-Time Video Super-Resolution

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Yan, Haojie Lu, Zhan Chen, Zehao Ma, De Tang, Huajin Zheng, Qian Pan, Gang The State Key Lab of Brain-Machine Intelligence Zhejiang University China College of Computer Science and Technology Zhejiang University China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)157735897X

In the domain of space-time video super-resolution, it is typically challenging to handle complex motions (including large and nonlinear motions) and varying illumination scenes due to the lack of inter-frame information. Leveraging the dense temporal information provided by event signals offers a promising solution. Traditional event-based methods typically rely on multiple images, using motion estimation and compensation, which can introduce errors. Accumulated errors from multiple frames often lead to artifacts and blurriness in the output. To mitigate these issues, we propose EvSTVSR, a method that uses fewer adjacent frames and integrates dense temporal information from events to guide alignment. Additionally, we introduce a coordinate-based feature fusion upsampling module to achieve spatial super-resolution. Experimental results demonstrate that our method not only outperforms existing RGB-based approaches but also excels in handling large motion scenarios. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perivascular spaces relate to the course and cognition of Huntington’s disease

引用

Translational Neurodegeneration 2023年第1期12卷 546-549页

作者： Xiao-Yan Li Juan-Juan Xie Jin-Hong Wang Yu-Feng Bao Yi Dong Bin Gao Ting Shen Pei-Yu Huang Hao-Chao Ying Han Xu Anna Wang Roe Hsin-Yi Lai Zhi-Ying Wu Department of Medical Genetics and Center for Rare Diseases Department of Neurology in Second Affiliated HospitalKey Laboratory of Medical Neurobiology of Zhejiang ProvinceZhejiang University School of MedicineHangzhouChina Interdisciplinary Institute of Neuroscience and Technology College of Biomedical Engineering and Instrument ScienceKey Laboratory for Biomedical Engineering of Ministry of EducationZhejiang UniversityHangzhouChina College of Computer Science and Technology Zhejiang UniversityHangzhouChina Department of Radiology Second Affiliated HospitalZhejiang University School of MedicineHangzhouChina School of Public Health Zhejiang UniversityHangzhouChina MOE Frontier Science Center for Brain Research and Brain-Machine Integration School of Brain Science and Brain MedicineZhejiang UniversityHangzhouChina CAS Center for Excellence in Brain Science and Intelligence Technology ShanghaiChina

Huntington’s disease(HD)is an autosomal dominant neurodegenerative disease that is caused by a cytosine-adenine-guanine(CAG)expansion in the first exon of the huntingtin(HTT)gene,which codes for the hun-tingtin *** typically manifests with a triad of symptoms,including motor disorders,cognitive impair-ment and psychiatric disturbances[1].HD primar-ily affects the basal ganglia(BG),especially the caudate and putamen,after which it extends to more widespread gray and white matter[2].Perivascular spaces(PVSs)are fluid-filled extensions of the subarachnoid spaces that enclose cerebral blood vessels and extend from the cer-ebral cortex through the brain *** physi-ological role of PVSs is the drainage of brain interstitial fluid into perivascular pathways for the elimination of waste products through the glymphatic drainage *** increasing number of studies have demonstrated that enlarged PVSs indicate glymphatic dysfunction and are associated with many neurological diseases,such as Alzheimer’s disease,Parkinson’s disease and small vessel disease[3].With the advantage of strong field strengths,7.0 T images show superior resolution and signal-to-noise ratios than 3.0 T,which facilitate the visualization of *** automated segmentation methods could accurately identify PVS in a short time with no inter-rater *** the current study,we used U-shaped networks(U-net),a class of deep learning methods,to explore the PVS distribution in HD and *** date,PVS distribution in HD is still *** two studies have investigated PVSs in HD,and both dem-onstrated increased visible PVS burden in manifest HD compared to controls[4,5].However,whether PVS bur-den increases in premanifest HD(pre-HD)individuals remains unknown,and the relationship of PVS with cog-nitive decline has never been studied.

关键词： Huntington filled elimination

来源：评论

学校读者我要写书评

暂无评论

EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks

arXiv

引用

arXiv 2024年

作者： Wang, Ziming Wang, Ziling Li, Huaning Qin, Lang Jiang, Runhao Ma, De Tang, Huajin College of Computer Science and Technology Zhejiang University Hangzhou310027 China State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection in scenarios with motion blur and challenging lighting conditions. However, while most existing approaches prioritize optimizing spatiotemporal representations with advanced detection backbones and early aggregation functions, the crucial issue of adaptive event sampling remains largely unaddressed. Spiking Neural Networks (SNNs), operating on an event-driven paradigm, align closely with the behavior of an ideal temporal event sampler. Motivated by this, we propose a novel adaptive sampling module that leverages recurrent convolutional SNNs enhanced with temporal memory, facilitating a fully end-to-end learnable framework for event-based detection. Additionally, we introduce Residual Potential Dropout (RPD) and Spike-Aware Training (SAT) to regulate potential distribution and address performance degradation encountered in spike-based sampling modules. Empirical evaluation on neuromorphic detection datasets demonstrates that our approach outperforms existing state-of-the-art spike-based methods with significantly fewer parameters and time steps. For instance, our method yields a 4.4% mAP improvement on the Gen1 dataset, while requiring 38% fewer parameters and only three time steps. Moreover, the applicability and effectiveness of our adaptive sampling methodology extend beyond SNNs, as demonstrated through further validation on conventional non-spiking models. Code is available at Github. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Tumor Micro-Environment Interactions Guided Graph Learning for Survival Analysis of Human Cancers from Whole-Slide Pathological Images

Tumor Micro-Environment Interactions Guided Graph Learning f...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wei Shao YangYang Shi Daoqiang Zhang JunJie Zhou Peng Wan Ministry of Education College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Key Laboratory of Brain-Machine Intelligence Technology Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The recent advance of deep learning technology brings the possibility of assisting the pathologist to predict the patients' survival from whole-slide pathological images (WSIs). However, most of the prevalent methods only worked on the sampled patches in specifically or randomly selected tumor areas of WSIs, which has very limited capability to capture the complex interactions between tumor and its surrounding micro-environment components. As a matter of fact, tumor is supported and nurtured in the heterogeneous tumor micro-environment(TME), and the detailed analysis of TME and their correlation with tumors are important to in-depth analyze the mechanism of cancer development. In this paper, we considered the spatial interactions among tumor and its two major TME components (i.e., lymphocytes and stromal fibrosis) and presented a Tumor Micro-environment Interactions Guided Graph Learning (TMEGL) algorithm for the prognosis prediction of human cancers. Specifically, we firstly selected different types of patches as nodes to build graph for each WSI. Then, a novel TME neighborhood organization guided graph embedding algorithm was proposed to learn node representations that can preserve their topological structure information. Finally, a Gated Graph Attention Network is applied to capture the survival-associated intersections among tumor and different TME components for clinical outcome prediction. We tested TMEGL on three cancer cohorts derived from The Cancer Genome Atlas (TCGA), and the experimental results indicated that TMEGL not only outperforms the existing WSI-based survival analysis models, but also has good explainable ability for survival prediction.

关键词： Pathology Analytical models Organizations Predictive models Semisupervised learning Prediction algorithms Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Darkit: A User-Friendly Software Toolkit for Spiking Large Language Model

arXiv

引用

arXiv 2024年

作者： Du, Xin Ye, Shifan Zheng, Qian Hu, Yangfan Yan, Rui Qi, Shunyu Chen, Shuyang Tang, Huajin Pan, Gang Deng, Shuiguang School of Software Technology Zhejiang University Zhejiang China College of Computer Science and Technology Zhejiang University Zhejiang China The State Key Lab of Brain-Machine Intelligence Zhejiang University Zhejiang China

Large language models (LLMs) have been widely applied in various practical applications, typically comprising billions of parameters, with inference processes requiring substantial energy and computational resources Brown [2020], Touvron et al. [2023]. In contrast, the human brain, employing bio-plausible spiking mechanisms, can accomplish the same tasks while significantly reducing energy consumption, even with a similar number of parameters Xing et al. [2024a]. Based on this, several pioneering researchers have proposed and implemented various large language models that leverage spiking neural networks Xing et al. [2024b], Zhu et al. [2023]. They have demonstrated the feasibility of these models, validated their performance, and open-sourced their frameworks and partial source code. To accelerate the adoption of brain-inspired large language models and facilitate secondary development for researchers, we are releasing a software toolkit named DarwinKit (Darkit). The toolkit is designed specifically for learners, researchers, and developers working on spiking large models, offering a suite of highly user-friendly features that greatly simplify the learning, deployment, and development processes. Copyright © 2024, The Authors. All rights reserved.

关键词： brain models

来源：评论

学校读者我要写书评

暂无评论

CASRL: Collision Avoidance with Spiking Reinforcement Learning Among Dynamic, Decision-Making Agents

CASRL: Collision Avoidance with Spiking Reinforcement Learni...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Chengjun Zhang Ka-Wa Yip Bo Yang Zhiyong Zhang Mengwen Yuan Rui Yan Huajin Tang Zhejiang Lab Research Institute of Intelligent Computing Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Developing an efficient collision avoidance policy with Spiking Reinforcement Learning for dynamic, decision-making agents remains challenging. Moreover, the implementation of energy-efficient collision avoidance is important for mobile robots that operate with limited on-board computing resources. Most existing energy-efficient methods via spiking reinforcement learning are predominately concerned with the navigational capabilities of a single agent, and are unable to handle a large, and possibly varying number of agents. To overcome these limitations, we propose a model called collision avoidance with spiking reinforcement learning (CASRL), based on proximal policy optimization algorithms. This proposed model consists of an actor with spiking neural networks (SNNs) and a critic with deep neural networks (DNNs). Our spiking reinforcement learning algorithm is advantageous to handle an arbitrary number of other agents by virtue of a spiking-gated transformer (SpikeGTr) architecture and an accumulate-to-fire (ATF) module. Extensive experimental results demonstrate that CASRL obtains a competitive success rate of navigation and exhibits higher time-efficiency for navigation in crowded scenarios compared to traditional DNN-based methods.

关键词： Training Visualization Navigation Heuristic algorithms Decision making Reinforcement learning Spiking neural networks Transformers Energy efficiency Collision avoidance

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：