检索结果-内蒙古大学图书馆

Deep molecular representation learning via fusing physical and chemical information 21

学校读者我要写书评

暂无评论

Deep molecular representation learning via fusing physical a...

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Shuwen Yang Ziyao Li Guojie Song Lingsheng Cai Key Laboratory of Machine Perception and Intelligence (MOE) Peking University Beijing China Center for Data Science Peking University Beijing China

ISBN: (纸本)9781713845393

Molecular representation learning is the frst yet vital step in combining deep learning and molecular science. To push the boundaries of molecular representation learning, we present PhysChem, a novel neural architecture that learns molecular representations via fusing physical and chemical information of molecules. PhysChem is composed of a physicist network (PhysNet) and a chemist network (ChemNet). PhysNet is a neural physical engine that learns molecular conformations through simulating molecular dynamics with parameterized forces; ChemNet implements geometry-aware deep message-passing to learn chemical / biomedical properties of molecules. Two networks specialize in their own tasks and cooperate by providing expertise to each other. By fusing physical and chemical information, PhysChem achieved state-of-the-art performances on MoleculeNet, a standard molecular machine learning benchmark. The effectiveness of PhysChem was further corroborated on cutting-edge datasets of SARS-CoV-2.

关键词：

Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Xiaoyu Zhong, Han Yang, Zhuoran Wang, Zhaoran Wang, Liwei Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Center for Data Science Peking University China Peng Cheng Laboratory China Department of Statistics and Data Science Yale University United States Department of Industrial Engineering and Management Sciences Northwestern University United States

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. The goal of the agent is to learn the optimal policy which is most preferred by the human overseer. Despite the empirical successes, the theoretical understanding of preference-based RL (PbRL) is only limited to the tabular case. In this paper, we propose the first optimistic model-based algorithm for PbRL with general function approximation, which estimates the model using value-targeted regression and calculates the exploratory policies by solving an optimistic planning problem. Our_ algorithm achieves the regret of Õ(poly(dH)√K), where d is the complexity measure of the transition and preference model depending on the Eluder dimension and log-covering numbers, H is the planning horizon, K is the number of episodes, and Õ(·) omits logarithmic terms. Our lower bound indicates that our algorithm is near-optimal when specialized to the linear setting. Furthermore, we extend the PbRL problem by formulating a novel problem called RL with n-wise comparisons, and provide the first sample-efficient algorithm for this new setting. To the best of our knowledge, this is the first theoretical result for PbRL with (general) function approximation. Copyright © 2022, The Authors. All rights reserved.

关键词： Approximation algorithms

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots

学校读者我要写书评

暂无评论

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 19-23页

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Faculty of Computing and Data Science FLAME University Maharashtra Pune India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023 The Authors

关键词： machine learning

MassSpecGym: A benchmark for the discovery and identification of molecules 38

学校读者我要写书评

暂无评论

MassSpecGym: A benchmark for the discovery and identificatio...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Bioinformatics Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of computing science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym - the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

DFingerNet: Noise-Adaptive Speech Enhancement for Hearing Aids

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tsangko, Iosif Triantafyllopoulos, Andreas Müller, Michael Schröter, Hendrik Schuller, Björn W. EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany CHI – Chair of Health Informatics Technical University of Munich Germany MCML – Munich Center for Machine Learning Munich Germany WS Audiology Research and Development Erlangen Germany GLAM – Group on Language Audio & Music Imperial College London United Kingdom MDSI – Munich Data Science Institute Munich Germany

关键词： Budget control

Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Ziwei Wang, Dong Chen, Yihong Wang, Ziteng Wang, Liwei Center for Data Science Peking University China Key Laboratory of Machine Perception MOE School of Artificial Intelligence Peking University China Yizhun Medical AI Co. Ltd China China Peng Cheng Laboratory China

Detecting mass in mammogram is significant due to the high occurrence and mortality of breast cancer. In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important. However, most of the existing methods build relatively coarse correspondence and have not utilized correspondence supervision. In this paper, we propose a new transformer-based framework CL-Net to learn lesion detection and pairwise correspondence in an end-to-end manner. In CL-Net, View-Interactive Lesion Detector is proposed to achieve dynamic interaction across candidates of cross views, while Lesion Linker employs the correspondence supervision to guide the interaction process more accurately. The combination of these two designs accomplishes precise understanding of pairwise lesion correspondence for mammograms. Experiments show that CL-Net yields state-of-the-art performance on the public DDSM dataset and our in-house dataset. Moreover, it outperforms previous methods by a large margin in low FPI regime. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

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

Touchstone benchmark: are we on the right way for evaluating AI algorithms for medical segmentation? 24

学校读者我要写书评

暂无评论

Touchstone benchmark: are we on the right way for evaluating...

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

作者： Pedro R. A. S. Bassi Wenxuan Li Yucheng Tang Fabian Isensee Zifu Wang Jieneng Chen Yu-Cheng Chou Saikat Roy Yannick Kirchhoff Maximilian Rokuss Ziyan Huang Jin Ye Junjun He Tassilo Wald Constantin Ulrich Michael Baumgartner Klaus H. Maier-Hein Paul Jaeger Yiwen Ye Yutong Xie Jianpeng Zhang Ziyang Chen Yong Xia Zhaohu Xing Lei Zhu Yousef Sadegheih Afshin Bozorgpour Pratibha Kumari Reza Azad Dorit Merhof Pengcheng Shi Ting Ma Yuxin Du Fan Bai Tiejun Huang Bo Zhao Haonan Wang Xiaomeng Li Hanxue Gu Haoyu Dong Jichen Yang Maciej A. Mazurowski Saumya Gupta Linshan Wu Jiaxin Zhuang Hao Chen Holger Roth Daguang Xu Matthew B. Blaschko Sergio Decherchi Andrea Cavalli Alan L. Yuille Zongwei Zhou Department of Computer Science Johns Hopkins University and Department of Pharmacy and Biotechnology University of Bologna and Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Department of Computer Science Johns Hopkins University NVIDIA Division of Medical Image Computing German Cancer Research Center (DKFZ) and Helmholtz Imaging German Cancer Research Center (DKFZ) ESAT-PSI KU Leuven Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University and HIDSS4Health - Helmholtz Information and Data Science School for Health Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Division of Medical Image Computing German Cancer Research Center (DKFZ) Division of Medical Image Computing German Cancer Research Center (DKFZ) and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Helmholtz Imaging German Cancer Research Center (DKFZ) and Interactive Machine Learning Group (IML) DKFZ School of Computer Science and Engineering Northwestern Polytechnical University Australian Institute for Machine Learning The University of Adelaide College of Computer Science and Technology Zhejiang University Hong Kong University of Science and Technology (Guangzhou) Hong Kong University of Science and Technology (Guangzhou) and Hong Kong University of Science and Technology Faculty of Informatics and Data Science University of Regensburg Faculty of Electrical Engineering and Information Technology RWTH Aachen University Faculty of Informatics and Data Science University of Regensburg and Fraunhofer Institute for Digital Medicine MEVIS Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shanghai Jiao Tong University and Beijing Academy of Artificial Intelligence (BAAI) S

ISBN: (纸本)9798331314385

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

关键词：

Eigenvectors of the De Bruijn Graph Laplacian: A Natural Basis for the Cut and Cycle Space

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Philippakis, Anthony Mallinar, Neil Pandit, Parthe Belkin, Mikhail GV 5 Cambridge Ctr CambridgeMA02142 United States The Broad Institute of MIT and Harvard 415 Main St CambridgeMA02142 United States Department of Computer Science and Engineering UC San Diego 3235 Voigt Dr San DiegoCA92093 United States Center for Machine Intelligence and Data Science IIT Bombay KReSIT Building IIT Powai Maharashtra Mumbai400076 India Halıcıoglu Data Science Institute UC San Diego 3234 Matthews Ln San DiegoCA92093 United States

We study the Laplacian of the undirected De Bruijn graph over an alphabet A of order k. While the eigenvalues of this Laplacian were found in 1998 by Delorme and Tillich [1], an explicit description of its eigenvectors has remained elusive. In this work, we find these eigenvectors in closed form and show that they yield a natural and canonical basis for the cut- and cycle-spaces of De Bruijn graphs. Remarkably, we find that the cycle basis we construct is a basis for the cycle space of both the undirected and the directed De Bruijn graph. This is done by developing an analogue of the Fourier transform on the De Bruijn graph, which acts to diagonalize the Laplacian. Moreover, we show that the cycle-space of De Bruijn graphs, when considering all possible orders of k simultaneously, contains a rich algebraic structure, that of a graded Hopf algebra. © 2024, CC BY.

关键词： Undirected graphs