检索结果-内蒙古大学图书馆

Towards self-driving laboratories: The central role of density functional theory in the AI age

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Bing von Rudorff, Guido Falk Anatole von Lilienfeld, O. University of Vienna Faculty of Physics Kolingasse 14-16 WienAT1090 Austria University Kassel Department of Chemistry Heinrich-Plett-Str.40 Kassel34132 Germany Heinrich-Plett-Straße 40 Kassel34132 Germany Vector Institute for Artificial Intelligence TorontoONM5S 1M1 Canada Department of Chemistry Materials Science and Engineering and Physics University of Toronto St. George Campus TorontoON Canada Machine Learning Group Technische Universität Berlin Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

Density functional theory (DFT) plays a pivotal role for the chemical and materials science due to its relatively high predictive power, applicability, versatility and computational efficiency. We review recent progress in machine learning model developments which has relied heavily on density functional theory for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in some broader context for the chemical and materials sciences. Resulting in DFT based machine learning models with high efficiency, accuracy, scalability, and transferability (EAST), recent progress indicates probable ways for the routine use of successful experimental planning software within self-driving laboratories. © 2023, CC0.

关键词： Density functional theory

Automatic Diagnosis of Myocarditis Disease in Cardiac MRI Modality using Deep Transformers and Explainable Artificial Intelligence

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jafari, Mahboobeh Shoeibi, Afshin Ghassemi, Navid Heras, Jonathan Ling, Sai Ho Beheshti, Amin Zhang, Yu-Dong Wang, Shui-Hua Alizadehsani, Roohallah Gorriz, Juan M. Acharya, U. Rajendra Rokny, Hamid Alinejad Internship in BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Data Science and Computational Intelligence Institute University of Granada Spain Department of Mathematics and Computer Science University of La Rioja La Rioja Spain Australia Data Analytics Lab Department of Computing Macquarie University SydneyNSW2109 Australia School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Deakin University VIC3217 Australia Department of Psychiatry University of Cambridge United Kingdom School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Data Science Hub The University of New South Wales SydneyNSW2052 Australia Research Centre Macquarie University Sydney2109 Australia

Myocarditis is a significant cardiovascular disease (CVD) that poses a threat to the health of many individuals by causing damage to the myocardium. The occurrence of microbes and viruses, including the likes of HIV, plays a crucial role in the development of myocarditis disease (MCD). The images produced during cardiac magnetic resonance imaging (CMRI) scans are low contrast, which can make it challenging to diagnose cardiovascular diseases. In other hand, checking numerous CMRI slices for each CVD patient can be a challenging task for medical doctors. To overcome the existing challenges, researchers have suggested the use of artificial intelligence (AI)-based computer-aided diagnosis systems (CADS). The presented paper outlines a CADS for the detection of MCD from CMR images, utilizing deep learning (DL) methods. The proposed CADS consists of several steps, including dataset, preprocessing, feature extraction, classification, and post-processing. First, the Z-Alizadeh dataset was selected for the experiments. Subsequently, the CMR images underwent various preprocessing steps, including denoising, resizing, as well as data augmentation (DA) via CutMix and MixUp techniques. In the following, the most current deep pre-trained and transformer models are used for feature extraction and classification on the CMR images. The findings of our study reveal that transformer models exhibit superior performance in detecting MCD as opposed to pre-trained architectures. In terms of DL architectures, the Turbulence Neural Transformer (TNT) model exhibited impressive accuracy, reaching 99.73% utilizing a 10-fold cross-validation approach. Additionally, to pinpoint areas of suspicion for MCD in CMRI images, the Explainable-based Grad Cam method was employed. © 2022, CC BY-NC-ND.

关键词： Diseases

Strain-induced superfluid transition for atoms on graphene

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kim, Sang Wook Elsayed, Mohamed Nichols, Nathan S. Lakoba, Taras Vanegas, Juan Wexler, Carlos Kotov, Valeri N. Maestro, Adrian Del Department of Physics University of Vermont BurlingtonVT05405 United States Data Science and Learning Division Argonne National Laboratory ArgonneIL60439 United States Department of Mathematics & Statistics University of Vermont BurlingtonVT05405 United States Department of Physics and Astronomy University of Missouri ColumbiaMO65211 United States Department of Physics and Astronomy University of Tennessee KnoxvilleTN37996 United States Min H. Kao Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN37996 United States

Bosonic atoms deposited on atomically thin substrates represent a playground for exotic quantum many-body physics due to the highly-tunable, atomic-scale nature of the interaction potentials. The ability to engineer strong interparticle interactions can lead to the emergence of complex collective atomic states of matter, not possible in the context of dilute atomic gases confined in optical lattices. While it is known that the first layer of adsorbed helium on graphene is permanently locked into a solid phase, we show by a combination of quantum Monte Carlo and mean-field techniques, that simple isotropic graphene lattice expansion effectively unlocks a large variety of two-dimensional ordered commensurate, incommensurate, cluster atomic solid, and superfluid states for adsorbed atoms. It is especially significant that an atomically thin superfluid phase of matter emerges under experimentally feasible strain values, with potentially supersolid phases in close proximity on the phase diagram. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphene

Large language models illuminate a progressive pathway to artificial intelligent healthcare assistant

学校读者我要写书评

暂无评论

Medicine Plus

Medicine Plus 2024年第2期1卷 102-124页

作者： Mingze Yuan Peng Bao Jiajia Yuan Yunhao Shen Zifan Chen Yi Xie Jie Zhao Quanzheng Li Yang Chen Li Zhang Lin Shen Bin Dong Center for Data Science Peking UniversityBeijing 100871China Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education)Peking University Cancer Hospital and Institute Beijing 100142China National Engineering Laboratory for Big Data Analysis and Applications Peking UniversityBeijing 100871China Beijing International Center for Mathematical Research Peking UniversityBeijing 100871China Center for Machine Learning Research Peking University Beijing 100871China National Biomedical Imaging Center Peking UniversityBeijing 100871China Peking University Changsha Institute for Computing and Digital Economy Changsha 410205China Massachusetts General Hospital Boston MA 02114-2696USA Harvard Medical School BostonMA 02115USA

With the rapid development of artificial intelligence,large language models(LLMs)have shown promising capabilities in mimicking human-level language comprehen-sion and *** has sparked significant interest in applying LLMs to enhance various aspects of healthcare,ranging from medical education to clinical decision ***,medicine involves multifaceted data modalities and nuanced reasoning skills,presenting challenges for integrating *** review introduces the fundamental applications of general-purpose and specialized LLMs,demon-strating their utilities in knowledge retrieval,research support,clinical workflow automation,and diagnostic *** the inherent multimodality of medicine,the review emphasizes the multimodal LLMs and discusses their ability to process diverse data types like medical imaging and electronic health records to augment diagnostic *** address LLMs'limitations regarding personalization and complex clinical reasoning,the review further explores the emerging develop-ment of LLM-powered autonomous agents for ***,it summarizes the evaluation methodologies for assessing LLMs'reliability and safety in medical *** have transformative potential in medicine;however,there is a pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice.

关键词： Large language models Artificial intelligence Medicine Healthcare assistant Prompt engineering In-context learning

Objective frequentist uncertainty quantification for atmospheric CO2 retrievals

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Patil, Pratik Kuusela, Mikael Hobbs, Jonathan Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States

The steadily increasing amount of atmospheric carbon dioxide (CO2) is affecting the global climate system and threatening the long-term sustainability of Earth's ecosystem. In order to better understand the sources and sinks of CO2, NASA operates the Orbiting Carbon Observatory-2 & 3 satellites to monitor CO2 from space. These satellites make passive radiance measurements of the sunlight reflected off the Earth's surface in different spectral bands, which are then inverted in an ill-posed inverse problem to obtain estimates of the atmospheric CO2 concentration. In this work, we propose a new CO2 retrieval method that uses known physical constraints on the state variables and direct inversion of the target functional of interest to construct well-calibrated frequentist confidence intervals based on convex programming. We compare the method with the current operational retrieval procedure, which uses prior knowledge in the form of probability distributions to regularize the problem. We demonstrate that the proposed intervals consistently achieve the desired frequentist coverage, while the operational uncertainties are poorly calibrated in a frequentist sense both at individual locations and over a spatial region in a realistic simulation experiment. We also study the influence of specific nuisance state variables on the length of the proposed intervals and identify certain key variables that can greatly reduce the final uncertainty given additional deterministic or probabilistic constraints, and develop a principled framework to incorporate such information into our *** Codes 62P12, 15A29, 62F30, 90C90 Copyright © 2020, The Authors. All rights reserved.

关键词： Carbon dioxide

Revealing excited states of rotational Bose–Einstein condensates

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yin, Jianyuan Huang, Zhen Cai, Yongyong Du, Qiang Zhang, Lei School of Mathematical Sciences Laboratory of Mathematics and Applied Mathematics Peking University Beijing100871 China Department of Mathematics National University of Singapore Singapore119076 Singapore Department of Mathematics University of California BerkeleyCA94720 United States School of Mathematical Sciences Beijing Normal University Beijing100875 China Department of Applied Physics and Applied Mathematics Data Science Institute Columbia University New YorkNY10027 United States Beijing International Center for Mathematical Research Center for Quantitative Biology Center for Machine Learning Research Peking University Beijing100871 China

Rotational Bose–Einstein condensates can exhibit quantized vortices as topological excitations. In this study, the ground and excited states of the rotational Bose–Einstein condensates are systematically studied by calculating the stationary points of the Gross–Pitaevskii energy functional. Various excited states and their connections at different rotational frequencies are revealed in solution landscapes constructed with the constrained high-index saddle dynamics method. Four excitation mechanisms are identified: vortex addition, rearrangement, merging, and splitting. We demonstrate changes in the ground state with increasing rotational frequencies and decipher the evolution of the stability of ground states. Copyright © 2023, The Authors. All rights reserved.

关键词： Excited states

Provable Tensor Completion with Graph Information

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Kaidong Wang, Yao Liao, Xiuwu Tang, Shaojie Yang, Can Meng, Deyu Center for Intelligent Decision-making and Machine Learning School of Management Xian Jiaotong University Shaan’xi Xi’an China Naveen Jindal School of Management The University of Texas at Dallas RichardsonTX United States Department of Mathematics The Hong Kong University of Science and Technology Hong Kong School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xian Jiaotong University Shaan’xi Xian China Macau Institute of Systems Engineering Macau University of Science and Technology Taipa China

Graphs, depicting the interrelations between variables, has been widely used as effective side information for accurate data recovery in various matrix/tensor recovery related applications. In this paper, we study the tensor completion problem with graph information. Current research on graph-regularized tensor completion tends to be task-specific, lacking generality and systematic approaches. Furthermore, a recovery theory to ensure performance remains absent. Moreover, these approaches overlook the dynamic aspects of graphs, treating them as static akin to matrices, even though graphs could exhibit dynamism in tensor-related scenarios. To confront these challenges, we introduce a pioneering framework in this paper that systematically formulates a novel model, theory, and algorithm for solving the dynamic graph regularized tensor completion problem. For the model, we establish a rigorous mathematical representation of the dynamic graph, based on which we derive a new tensor-oriented graph smoothness regularization. By integrating this regularization into a tensor decomposition model based on transformed t-SVD, we develop a comprehensive model simultaneously capturing the low-rank and similarity structure of the tensor. In terms of theory, we showcase the alignment between the proposed graph smoothness regularization and a weighted tensor nuclear norm. Subsequently, we establish assurances of statistical consistency for our model, effectively bridging a gap in the theoretical examination of the problem involving tensor recovery with graph information. In terms of the algorithm, we develop a solution of high effectiveness, accompanied by a guaranteed convergence, to address the resulting model. To showcase the prowess of our proposed model in contrast to established ones, we provide in-depth numerical experiments encompassing synthetic data as well as real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Tensors

Your transformer may not be as powerful as you expect 22

学校读者我要写书评

暂无评论

Your transformer may not be as powerful as you expect

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shengjie Luo Shanda Li Shuxin Zheng Tie-Yan Liu Liwei Wang Di He National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Zhejiang Lab Machine Learning Department School of Computer Science Carnegie Mellon University Microsoft Research National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University

ISBN: (纸本)9781713871088

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based Transformers is largely unexplored. In this work, we mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. One may naturally assume the answer is in the affirmative—RPE-based Transformers are universal function approximators. However, we present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. One key reason lies in that most RPEs are placed in the softmax attention that always generates a right stochastic matrix. This restricts the network from capturing positional information in the RPEs and limits its capacity. To overcome the problem and make the model more powerful, we first present sufficient conditions for RPE-based Transformers to achieve universal function approximation. With the theoretical guidance, we develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions. Therefore, the corresponding URPE-based Transformers become universal function approximators. Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications.

关键词：

Universal consistency of deep convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lin, Shao-Bo Wang, Kaidong Wang, Yao Zhou, Ding-Xuan Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an710049 China School of Data Science Department of Mathematics City University of Hong Kong Hong Kong Hong Kong

Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind. In particular, the universal consistency of DCNNs remains open. In this paper, we prove that implementing empirical risk minimization on DCNNs with expansive convolution (with zero-padding) is strongly universally consistent. Motivated by the universal consistency, we conduct a series of experiments to show that without any fully connected layers, DCNNs with expansive convolution perform not worse than the widely used deep neural networks with hybrid structure containing contracting (without zero-padding) convolution layers and several fully connected layers. © 2021, CC BY.

关键词： Deep neural networks