检索结果-内蒙古大学图书馆

Propagation of waves in fractal spaces

学校读者我要写书评

暂无评论

Waves in Random and Complex Media 2023年

作者： El-Nabulsi, Rami Ahmad Golmankhaneh, Alireza Khalili Center of Excellence in Quantum Technology Faculty of Engineering Chiang Mai University Chiang Mai Thailand Quantum-Atom Optics Laboratory and Research Center for Quantum Technology Faculty of Science Chiang Mai University Chiang Mai Thailand Department of Physics and Materials Science Faculty of Science Chiang Mai University Chiang Mai Thailand Artificial Intelligence and Big Data Automation Research Center Urmia Branch Islamic Azad University Urmia Iran

In this study, we study waves propagation in fractal spaces based on two independent variational approaches: the first one is based on the ‘product-like fractal measure’ introduced by Li and Ostoja-Starzewski in their analysis of nonlinear fractal dynamics in anisotropic porous media whereas the second and another is based on fractal calculus, which includes analytical functions with fractal support. The first approach is motivating since it describes physics in anisotropic media characterized by fractal dimensions. The second one is also of particular importance since it offers a new framework to reformulate the laws of physics in spaces with fractional dimensions. In both approaches, the fractional Laplace equation is derived and solved using plausible boundary conditions. This study proves the importance of fractals in wave motion We show that these models are able to describe the propagation of waves in a fractal Hausdorff dimensional space. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Wave propagation

Deep Learning-Based Point Cloud Registration: A Comprehensive Survey and Taxonomy

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yu-Xin Gui, Jie Yu, Baosheng Cong, Xiaofeng Gong, Xin Tao, Wenbing Tao, Dacheng School of Cyber Science and Engineering Southeast University Nanjing210000 China Purple Mountain Laboratories Nanjing210000 China Lee Kong Chian School of Medicine Nanyang Technological University 308232 Singapore School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue Singapore639798 Singapore

Point cloud registration involves determining a rigid transformation to align a source point cloud with a target point cloud. This alignment is fundamental in applications such as autonomous driving, robotics, and medical imaging, where precise spatial correspondence is essential. Deep learning has greatly advanced point cloud registration by providing robust and efficient methods that address the limitations of traditional approaches, including sensitivity to noise, outliers, and initialization. However, a well-constructed taxonomy for these methods is still lacking, making it difficult to systematically classify and compare the various approaches. In this paper, we present a comprehensive survey and taxonomy on deep learning-based point cloud registration (DL-PCR). We begin with a formal description of the point cloud registration problem, followed by an overview of the datasets, evaluation metrics, and loss functions commonly used in DL-PCR. Next, we categorize existing DL-PCR methods into supervised and unsupervised approaches, as they focus on significantly different key aspects. For supervised DL-PCR methods, we organize the discussion based on key aspects, including the registration procedure, optimization strategy, learning paradigm, network enhancement, and integration with traditional methods;For unsupervised DL-PCR methods, we classify them into correspondence-based and correspondence-free approaches, depending on whether they require explicit identification of point-to-point correspondences. To facilitate a more comprehensive and fair comparison, we conduct quantitative evaluations of all recent state-of-the-art approaches, using a unified training setting and consistent data partitioning strategy. Lastly, we highlight the open challenges and discuss potential directions for future study. We hope this comprehensive survey will contribute to the advancement of DL-PCR by serving as a fundamental reference for researchers and practitioners in the field. A c

关键词： Taxonomies

Monte-Carlo tree search with uncertainty propagation via optimal transport

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dam, Tuan Stenger, Pascal Schneider, Lukas Pajarinen, Joni D'Eramo, Carlo Maillard, Odalric-Ambrym Univ. Lille Inria CNRS Centrale Lille UMR 9189-CRIStAL LilleF-59000 France Department of Computer Science Technical University of Darmstadt Germany ETHZ - ETH Zurich Switzerland Department of Electrical Engineering and Automation Aalto University Finland Center for Artificial Intelligence and Data Science University of Würzburg Germany Hessian.ai Germany

This paper introduces a novel backup strategy for Monte-Carlo Tree Search (MCTS) designed for highly stochastic and partially observable Markov decision processes. We adopt a probabilistic approach, modeling both value and action-value nodes as Gaussian distributions. We introduce a novel backup operator that computes value nodes as the Wasserstein barycenter of their action-value children nodes;thus, propagating the uncertainty of the estimate across the tree to the root node. We study our novel backup operator when using a novel combination of L1-Wasserstein barycenter with α-divergence, by drawing a notable connection to the generalized mean backup operator. We complement our probabilistic backup operator with two sampling strategies, based on optimistic selection and Thompson sampling, obtaining our Wasserstein MCTS algorithm. We provide theoretical guarantees of asymptotic convergence to the optimal policy, and an empirical evaluation on several stochastic and partially observable environments, where our approach outperforms well-known related baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Uncertainty analysis

Sentiment Analysis on Drug Reviews Using Diverse Classification Techniques

学校读者我要写书评

暂无评论

Sentiment Analysis on Drug Reviews Using Diverse Classificat...

Communication, Computing and Industry 4.0 (C2I4), International Conference on

作者： Premkumar Duraisamy Yuvaraj Natarajan K.R.Sri Preethaa K. Mouthami Department of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Research Professor Intelligent Construction Automation Center Kyungpook National University Deagu South Korea

ISBN: (数字)9781665474979

ISBN: (纸本)9781665474986

Free text reviews are abundantly distributed over the internet among the standard population of the world. Although online doctors were consulted during the pandemic, many drugs are taken without prescription by ordinary people. Reviews are distributed about the medicines through online feeds, posts and blogs, which are merely helpful in identifying the side effects and their adverse reactions in combination with another drug or standalone adverse reactions. Spelling mistakes, jargon and short names are normalized throughout the medical terminologies using Natural language processing (NLP) and RxNorm from the reviews extracted from these sources. The concept of Bidirectional Encoder Representations from Transformers (BERT) is used to mine the association rules for the drug interactions when used in conjugation with another drug, and the idea of Adaptive Fuzzy logic neural networks is used to validate the results of association rules derived from the BERT. Inconsistencies identified by the regulations generated were rejected efficiently by the Support vector machines (SVM), Radial Basis Function (RBF)and the system shows 60.11 percentage of accuracy with 10 cross-fold validation, whereas the results are equivalent to the accuracy obtained using SVM with RBF kernel. The data set is reduced from its dimension using Linear discriminant analysis (LDA) by applying the mining process and BERT on two drugs, namely “Azithromycin” in conjugation with Buprenorphine has Type ‘A’ side effects, and Prozac in conjugation with Metronidazole shows different side effects. Deplin and Zoloft give very positive symptoms and are independent of dosage interactions.

关键词： Support vector machines Drugs Analytical models Terminology Bit error rate Support vector machine classification Transformers

Policy Representation via Diffusion Probability Model for Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Long Huang, Zhixiong Lei, Fenghao Zhong, Yucun Yang, Yiming Fang, Cong Wen, Shiting Zhou, Binbin Lin, Zhouchen School of Artificial Intelligence Peking University Beijing China College of Computer Science and Technology Zhejiang University China MOE Frontiers Science Center for Brain and Brain-Machine Integration College of Computer Science Zhejiang University China Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Data Engineering NingboTech University China College of Computer Science and Technology Hangzhou City University China

Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to learn complicated multimodal distributions, which has shown promising and potential applications to RL. In this paper, we formally build a theoretical foundation of policy representation via the diffusion probability model and provide practical implementations of diffusion policy for online model-free RL. Concretely, we character diffusion policy as a stochastic process induced by stochastic differential equations, which is a new approach to representing a policy. Then we present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. Furthermore, we propose the DIPO, which implements model-free online RL with DIffusion POlicy. To the best of our knowledge, DIPO is the first algorithm to solve model-free online RL problems with the diffusion model. Finally, extensive empirical results show the effectiveness and superiority of DIPO on the standard continuous control Mujoco benchmark. © 2023, CC BY.

关键词： Reinforcement learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

Spiking transformer with experts mixture 24

学校读者我要写书评

暂无评论

Spiking transformer with experts mixture

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhaokun Zhou Yijie Lu Yanhao Jia Kaiwei Che Jun Niu Liwei Huang Xinyu Shi Yuesheng Zhu Guoqi Li Zhaofei Yu Li Yuan School of Electronic and Computer Engineering Shenzhen Graduate School Peking University and Peng Cheng Laboratory School of Electronic and Computer Engineering Shenzhen Graduate School Peking University College of Computing and Data Science Nanyang Technological University and Deep NeuroCognition Lab I2R and CFAR Agency for Science Technology and Research School of Computer Science Peking University and Peng Cheng Laboratory Institute for Artificial Intelligence Peking University and School of Computer Science Peking University Institute of Automation Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9798331314385

Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing model capacity and conditional computation. In this work, we consider how to incorporate SNNs' spike-driven and MoE's conditional computation into a unified framework. However, MoE uses softmax to get the dense conditional weights for each expert and TopK to hard-sparsify the network, which does not fit the properties of SNNs. To address this issue, we reformulate MoE in SNNs and introduce the Spiking Experts Mixture Mechanism (SEMM) from the perspective of sparse spiking activation. Both the experts and the router output spiking sequences, and their element-wise operation makes SEMM computation spike-driven and dynamic sparse-conditional. By developing SEMM into Spiking Transformer, the Experts Mixture Spiking Attention (EMSA) and the Experts Mixture Spiking Perceptron (EMSP) are proposed, which performs routing allocation for head-wise and channel-wise spiking experts, respectively. Experiments show that SEMM realizes sparse conditional computation and obtains a stable improvement on neuromorphic and static datasets with approximate computational overhead based on the Spiking Transformer baselines.

关键词：

Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Handa, Palak Mahbod, Amirreza Schwarzhans, Florian Woitek, Ramona Goel, Nidhi Dhir, Manas Chhabra, Deepti Jha, Shreshtha Sharma, Pallavi Thakur, Vijay Chawla, Simarpreet Singh Gunjan, Deepak Kakarla, Jagadeesh Raman, Balasubramanian Research Center for Medical Image Analysis and Artificial Intelligence Department of Medicine Danube Private University Krems Austria Department of Electronics and Communication Engineering Indira Gandhi Delhi Technical University for Women Delhi India Department of Artificial Intelligence and Data Sciences Indira Gandhi Delhi Technical University for Women Delhi India Department of Artificial Intelligence and Machine Learning University School of Automation and Robotics Guru Gobind Singh Indraprastha University Delhi India Department of Electronics and Communication Engineering Delhi Technological University Delhi India Columbia University New YorkNY United States Department of Gastroenterology and HNU All India Institute of Medical Sciences Delhi India Chennai Kancheepuram India Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

We present the Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy. It was virtually organized by the Research Center for Medical Image Analysis and artificial intelligence (MIAAI), Department of Medicine, Danube Private University, Krems, Austria in collaboration with the 9th International Conference on Computer Vision & Image Processing (CVIP 2024) being organized by the Indian Institute of Information Technology, Design and Manufacturing (IIITDM) Kancheepuram, Chennai, India. This document provides an overview of the challenge, including the registration process, rules, submission format, description of the datasets used, qualified team rankings, all team descriptions, and the benchmarking results reported by the organizers. © 2024, CC BY.

关键词： Endoscopy

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos 38

学校读者我要写书评

暂无评论

Retrospective for the Dynamic Sensorium Competition for pred...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Turishcheva, Polina Fahey, Paul G. Vystrčilová, Michaela Hansel, Laura Froebe, Rachel Ponder, Kayla Qiu, Yongrong Willeke, Konstantin F. Bashiri, Mohammad Baikulov, Ruslan Zhu, Yu Ma, Lei Yu, Shan Huang, Tiejun Li, Bryan M. De Wulf, Wolf Kudryashova, Nina Hennig, Matthias H. Rochefort, Nathalie L. Onken, Arno Wang, Eric Ding, Zhiwei Tolias, Andreas S. Sinz, Fabian H. Ecker, Alexander S. Institute of Computer Science and Campus Institute Data Science University of Göttingen Germany Department of Neuroscience Center for Neuroscience and Artificial Intelligence Baylor College of Medicine HoustonTX United States Department of Ophthalmology Byers Eye Institute Stanford University School of Medicine StanfordCA United States Stanford Bio-X Stanford University StanfordCA United States Wu Tsai Neurosciences Institute Stanford University StanfordCA United States International Max Planck Research School for Intelligent Systems Tübingen Germany Institute for Bioinformatics and Medical Informatics Tübingen University Germany lRomul Russia Institute of Automation Chinese Academy of Sciences China Beijing Academy of Artificial Intelligence China The Alan Turing Institute United Kingdom School of Informatics University of Edinburgh United Kingdom Centre for Discovery Brain Sciences University of Edinburgh United Kingdom Simons Initiative for the Developing Brain University of Edinburgh United Kingdom Department of Electrical Engineering Stanford University StanfordCA United States Max Planck Institute for Dynamics and Self-Organization Göttingen Germany

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Machine learning has benefited tremendously from benchmarks that compare different models on the same task under standardized conditions. However, there was no standardized benchmark to identify state-of-the-art dynamic models of the mouse visual system. To address this gap, we established the SENSORIUM 2023 Benchmark Competition with dynamic input, featuring a new large-scale dataset from the primary visual cortex of ten mice. This dataset includes responses from 78,853 neurons to 2 hours of dynamic stimuli per neuron, together with behavioral measurements such as running speed, pupil dilation, and eye movements. The competition ranked models in two tracks based on predictive performance for neuronal responses on a held-out test set: one focusing on predicting in-domain natural stimuli and another on out-of-distribution (OOD) stimuli to assess model generalization. As part of the NeurIPS 2023 Competition Track, we received more than 160 model submissions from 22 teams. Several new architectures for predictive models were proposed, and the winning teams improved the previous state-of-the-art model by 50%. Access to the dataset as well as the benchmarking infrastructure will remain online at ***. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：