检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Aggregation in Ensembles of Multilabel Classifiers 23rd

On Aggregation in Ensembles of Multilabel Classifiers

引用

23rd International Conference on Discovery science, DS 2020

作者： Nguyen, Vu-Linh Hüllermeier, Eyke Rapp, Michael Loza Mencía, Eneldo Fürnkranz, Johannes Heinz Nixdorf Institute and Department of Computer Science Paderborn University Paderborn Germany Knowledge Engineering Group TU Darmstadt Darmstadt Germany Computational Data Analytics Group JKU Linz Linz Austria

ISBN: (纸本)9783030615260

While a variety of ensemble methods for multilabel classification have been proposed in the literature, the question of how to aggregate the predictions of the individual members of the ensemble has received little attention so far. In this paper, we introduce a formal framework of ensemble multilabel classification, in which we distinguish two principal approaches: "predict then combine" (PTC), where the ensemble members first make loss minimizing predictions which are subsequently combined, and "combine then predict" (CTP), which first aggregates information such as marginal label probabilities from the individual ensemble members, and then derives a prediction from this aggregation. While both approaches generalize voting techniques commonly used for multilabel ensembles, they allow to explicitly take the target performance measure into account. Therefore, concrete instantiations of CTP and PTC can be tailored to concrete loss functions. Experimentally, we show that standard voting techniques are indeed outperformed by suitable instantiations of CTP and PTC, and provide some evidence that CTP performs well for decomposable loss functions, whereas PTC is the better choice for non-decomposable losses. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal–organic frameworks for carbon capture

arXiv

引用

arXiv 2023年

作者： Park, Hyun Yan, Xiaoli Zhu, Ruijie Huerta, Eliu A. Chaudhuri, Santanu Cooper, Donny Foster, Ian Tajkhorshid, Emad Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Theoretical and Computational Biophysics Group NIH Resource Center for Macromolecular Modeling and Visualization Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Center for Biophysics and Quantitative Biology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Multiscale Materials and Manufacturing Lab University of Illinois Chicago ChicagoIL60607 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Computer Science University of Chicago ChicagoIL60637 United States Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States Computational Science and Engineering Data Science and AI Department TotalEnergies EP Research & Technology USA LLC HoustonTX77002 United States Department of Biochemistry University of Illinois at Urbana-Champaign UrbanaIL61801 United States

Metal–organic frameworks (MOFs) exhibit great promise for CO2 capture. However, finding the best performing materials poses computational and experimental grand challenges in view of the vast chemical space of potential building blocks. Here, we introduce GHP-MOFassemble, a generative artificial intelligence (AI), high performance framework for the rational and accelerated design of MOFs with high CO2 adsorption capacity and synthesizable linkers. GHP-MOFassemble generates novel linkers, assembled with one of three pre-selected metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer) into MOFs in a primitive cubic topology. GHP-MOFassemble screens and validates AI-generated MOFs for uniqueness, synthesizability, structural validity, uses molecular dynamics simulations to study their stability and chemical consistency, and crystal graph neural networks and Grand Canonical Monte Carlo simulations to quantify their CO2 adsorption capacities. We present the top six AI-generated MOFs with CO2 capacities greater than 2m molg−1, i.e., higher than 96.9% of structures in the hypothetical MOF dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Towards a Quantum Algorithm for the Incompressible Nonlinear Navier-Stokes Equations

Towards a Quantum Algorithm for the Incompressible Nonlinear...

引用

Quantum Computing and engineering (QCE), IEEE International Conference on

作者： Muralikrishnan Gopalakrishnan Meena Yu Zhang Weiwen Jiang Youzuo Lin Stefanie Günther Xinfeng Gao National Center for Computational Sciences Oak Ridge National Laboratory Oak Ridge TN USA Theoretical Division Los Alamos National Laboratory Los Alamos NM USA Department of Electrical and Computer Engineering George Mason University Fairfax VA USA School of Data Science and Society University of North Carolina at Chapel Hill Chapel Hill NC USA Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA USA Department of Mechanical and Aerospace Engineering University of Virginia Charlottesville VA USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

In this work, we present novel concepts for quantum algorithms to solve transient, nonlinear partial differential equations (PDEs). The challenge lies in how to effectively represent, encode, process, and evolve the nonlinear system of PDEs on quantum computers. We will discuss the new techniques using the incompressible Navier-Stokes equations as an example, because it represents the fundamental nonlinear feature and yet removes certain complexity in physics, allowing us to focus on the design of quantum algorithms. Previous attempts solving nonlinear PDEs in quantum computation have often involved storing multiple copies of solutions or employing linearizations. Neither is practical due to exponential scaling with evolution time or insufficient solution accuracy. We propose a new framework based on matrix product states (MPSs) and matrix product operators (MPOs), in addition to the Krylov subspace methods. For example, the solution variables of the Navier-Stokes equations are represented by MPSs, and the linear and nonlinear terms are processed by MPOs. The time evolution of the operators is attained by a fast-forwarding algorithm using Krylov subspace methods. Furthermore, we discuss various techniques for efficient encoding of MPSs, measurement reduction for MPOs, and use of tensor operations to treat multi-variate, multi-physics characteristics of Navier-Stokes.

关键词： computers Quantum algorithm Tensors Fluids Partial differential equations Encoding Transient analysis Nonlinear systems Physics Navier-Stokes equations

来源：评论

学校读者我要写书评

暂无评论

Foundations of symbolic languages for model interpretability

arXiv

引用

arXiv 2021年

作者： Arenas, Marcelo Baez, Daniel Barceló, Pablo Pérez, Jorge Subercaseaux Roa, Bernardo Anibal Department of Computer Science PUC-Chile Chile Institute for Mathematical and Computational Engineering PUC-Chile Chile Department of Computer Science Universidad de Chile Chile Millennium Institute for Foundational Research on Data Chile Carnegie Mellon University United States

Several queries and scores have recently been proposed to explain individual predictions over ML models. Given the need for flexible, reliable, and easy-to-apply interpretability methods for ML models, we foresee the need for developing declarative languages to naturally specify different explainability queries. We do this in a principled way by rooting such a language in a logic, called FOIL, that allows for expressing many simple but important explainability queries, and might serve as a core for more expressive interpretability languages. We study the computational complexity of FOIL queries over two classes of ML models often deemed to be easily interpretable: decision trees and OBDDs. Since the number of possible inputs for an ML model is exponential in its dimension, the tractability of the FOIL evaluation problem is delicate but can be achieved by either restricting the structure of the models or the fragment of FOIL being evaluated. We also present a prototype implementation of FOIL wrapped in a high-level declarative language and perform experiments showing that such a language can be used in practice. © 2021, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Latent Space Optimization of Generative Molecular Design Models

arXiv

引用

arXiv 2022年

作者： Nafiz Abeer, A.N.M. Urban, Nathan M. Ryan Weil, M. Alexander, Francis J. Yoon, Byung-Jun Department of Electrical and Computer Engineering Texas A&M University College StationTX77843 United States Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States Strategic and Data Science Initiatives Frederick National Laboratory FrederickMD21702 United States Argonne National Laboratory LemontIL60439 United States

Molecular design based on generative models, such as variational autoencoders (VAEs), has become increasingly popular in recent years due to its efficiency for exploring high-dimensional molecular space to identify molecules with desired properties. While the efficacy of the initial model strongly depends on the training data, the sampling efficiency of the model for suggesting novel molecules with enhanced properties can be further enhanced via latent space optimization. In this paper, we propose a multi-objective latent space optimization (LSO) method that can significantly enhance the performance of generative molecular design (GMD). The proposed method adopts an iterative weighted retraining approach, where the respective weights of the molecules in the training data are determined by their Pareto efficiency. We demonstrate that our multi-objective GMD LSO method can significantly improve the performance of GMD for jointly optimizing multiple molecular properties. © 2022, CC BY-NC-SA.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

An Effective Learning Management System for Revealing Student Performance Attributes

arXiv

引用

arXiv 2024年

作者： Zhang, Xinyu Lee, Vincent C.S. Xu, Duo Chen, Jun Obaidat, Mohammad S. The School of Electronics and Information Northwestern Polytechnical University Xi’an710072 China The Department of Data Science and Artificial Intelligence Faculty of IT Monash University Melbourne3800 Australia Guangyuan Foreign Language School Guangyuan628018 China Chongqing Institute for Brain and Intelligence Guangyang Bay Laboratory Chongqing400064 China The King Abdullah II School of Information Technology The University of Jordan Amman11942 Jordan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China Department of Computational Intelligence School of Computing SRM University SRM Nagar TN Kattankulathur603203 India School of Engineering The Amity University UP Noida201301 India

Contribution: A learning management system (LMS) incorporated with an advanced educational data mining module is proposed, as a means to mine efficiently from student performance records to provide valuable insights for educators in helping plan effective learning pedagogies, improve curriculum design, and guarantee quality of teaching. Background: An LMS streamlines the management of the teaching process in a centralized place, recording, tracking, and reporting the delivery of educational courses and student performance. Educational knowledge discovery from such an elearning system plays a crucial role in rule regulation, policy establishment, and system development. However, existing LMSs do not have embedded mining modules to directly extract knowledge. As educational modes become more complex, educational data mining efficiency from those heterogeneous student learning behaviours is gradually degraded. Intended outcomes: The design and application of the LMS enable educators to learn from past student performance experiences, empowering them to guide and intervene with students in time, and eventually improve their academic success. Application design: This study proposes an effective LMS which processes the stored data through an advanced educational data mining module. The mining module utilizes probability-based frequent pattern mining for generating candidate itemsets and updating LMS databases in each iteration for complexity reduction. In addition, the conditional probability increment ratio (CPIR) is deployed as an exceptionality measure to mine effective common and exception rules simultaneously. The iteratively generated rules can reveal academic performance patterns so that have merits in learning personal goal achievement. Findings: Through two illustrative case studies, experimental results demonstrate increased mining efficiency of the proposed mining module without information loss compared to classic educational mining algorithms. The mined knowl

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

arXiv

引用

arXiv 2022年

作者： Moridian, Parisa Ghassemi, Navid Jafari, Mahboobeh Salloum-Asfar, Salam Sadeghi, Delaram Khodatars, Marjane Shoeibi, Afshin Khosravi, Abbas Ling, Sai Ho Subasi, Abdulhamit Alizadehsani, Roohallah Gorriz, Juan M. Abdulla, Sara A. Acharya, U. Rajendra Faculty of Engineering Science and Research Branch Islamic Azad University Tehran Iran Computer Engineering Department Ferdowsi University of Mashhad Mashhad Iran Electrical and Computer Engineering Faculty Semnan University Semnan Iran Neurological Disorders Research Center Qatar Biomedical Research Institute Hamad Bin Khalifa University Qatar Foundation Doha Qatar Dept. of Medical Engineering Mashhad Branch Islamic Azad University Mashhad Iran Data Science and Computational Intelligence Institute University of Granada Granada Spain Deakin University GeelongVIC Australia UltimoNSW Australia Institute of Biomedicine Faculty of Medicine University of Turku Turku Finland Dept. of Computer Science College of Engineering Effat University Jeddah Saudi Arabia Ngee Ann Polytechnic Singapore Singapore Department of Biomedical Informatics and Medical Engineering Asia University Taichung Taiwan Department of Biomedical Engineering School of Science and Technology Singapore University of Social Sciences Singapore

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming;therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging. © 2022, CC BY-NC-ND.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Brief Review of Explainable Artificial Intelligence in Healthcare

arXiv

引用

arXiv 2023年

作者： Sadeghi, Zahra Alizadehsani, Roohallah Cifci, Mehmet Akif Kausar, Samina Rehman, Rizwan Mahanta, Priyakshi Bora, Pranjal Kumar Almasri, Ammar Alkhawaldeh, Rami S. Hussain, Sadiq Alatas, Bilal Shoeibi, Afshin Moosaei, Hossein Hladík, Milan Nahavandi, Saeid Pardalos, Panos M. Institute for Big Data Analytics Faculty of Computer Science Dalhousie University Canada Deakin University Geelong Australia The Institute of Computer Technology Tu Wien University Vienna1040 Austria University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Centre for Computer Science and Applications Dibrugarh University Assam India Department of Management Information Sys Al-Balqa Applied University Salt19117 Jordan Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Examination Branch Dibrugarh University Assam Dibrugarh India Department of Software Eng. Firat University Elazig23100 Turkey Data Science and Computational Intelligence Institute University of Granada Spain Department of Informatics Faculty of Science Jan Evangelista Purkyně University in Ústí nad Labem Czech Republic Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida Gainesville32611 United States

XAI refers to the techniques and methods for building AI applications which assist end users to interpret output and predictions of AI models. Black box AI applications in high-stakes decision-making situations, such as medical domain have increased the demand for transparency and explainability since wrong predictions may have severe consequences. Model explainability and interpretability are vital successful deployment of AI models in healthcare practices. AI applications' underlying reasoning needs to be transparent to clinicians in order to gain their trust. This paper presents a systematic review of XAI aspects and challenges in the healthcare domain. The primary goals of this study are to review various XAI methods, their challenges, and related machine learning models in healthcare. The methods are discussed under six categories: Features-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric methods. Most importantly, the paper explores XAI role in healthcare problems to clarify its necessity in safety-critical applications. The paper intends to establish a comprehensive understanding of XAI-related applications in the healthcare field by reviewing the related experimental results. To facilitate future research for filling research gaps, the importance of XAI models from different viewpoints and their limitations are investigated. © 2023, CC BY-NC-ND.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

arXiv

引用

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

关键词： Large datasets

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：