检索结果-内蒙古大学图书馆

The Fused Multiply-Add and Global Atmospheric Models: A Distributional Investigation into a Surprising Correctness Scenario

学校读者我要写书评

暂无评论

The Fused Multiply-Add and Global Atmospheric Models: A Dist...

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Teo Price-Broncucia Allison H. Baker Michael Duda Department of Computer Science University of Colorado Boulder CO Computational and Information Systems Lab NSF National Center for Atmospheric Research Boulder CO Mesoscale and Microscale Meteorology Lab NSF National Center for Atmospheric Research Boulder CO

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

In a series of related works developing an ensemble consistency testing approach for multiple popular global climate models (GCMs), one test scenario has repeatedly stood out. Why does the use of the Fused Multiply-Add (FMA) operation result in model configurations getting flagged as failures, while changes to compiler choice, optimization level, processor type and number, etc. are passed as expected? This work explores the impacts of FMA on GCM simulation output from a distributional perspective and provides directions for future work to enable model developers and users to use numerical optimization techniques with confidence.

关键词： Analytical models Atmospheric modeling computational modeling High performance computing Conferences Numerical models Optimization Testing Meteorology

LinkMed: Entity Recognition and Relation Extraction from Clinical Notes in Spanish

学校读者我要写书评

暂无评论

LinkMed: Entity Recognition and Relation Extraction from Cli...

2023 Iberian Languages Evaluation Forum, IberLEF 2023

作者： Muñoz-Castro, Carlos Carvallo, Andrés Rojas, Matías Aracena, Claudio Guerra, Rodrigo Pizarro, Benjamín Dunstan, Jocelyn National Center for Artificial Intelligence Chile Faculty of Physical and Mathematical Sciences Universidad de Chile Chile Department of Computer Science Pontificia Universidad Católica de Chile Chile Institute for Mathematical and Computational Engineering Pontificia Universidad Católica de Chile Chile Center for Mathematical Modeling Universidad de Chile Chile Millenium Institute Foundational Research on Data Chile

Relation extraction is an essential component of Natural Language Processing (NLP) and significantly influences information retrieval and structured information extraction. Within clinical notes, the task is needed to establish connections among illnesses, therapies, indications, and other medical concepts. Motivated by the above, in this work, we propose a two-step model approach for entity linking;in the first step, we solve entity recognition, and in the second, a relation classification approach. We evaluated our approach in a Spanish corpus of the TESTLINK challenge in IberLEF2023 (Iberian Languages Evaluation Forum), comprising 81 clinical notes to train and 80 clinical notes to test. Our results show competitive performance with a precision of 0.47, recall of 0.43, and F1-score of 0.45, presenting an effective strategy for relation extraction from clinical notes in Spanish. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Information retrieval

Evaluation of Deep Neural Operator Models toward Ocean Forecasting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rajagopal, Ellery Babu, Anantha N.S. Ryu, Tony Haley, Patrick J. Mirabito, Chris Lermusiaux, Pierre F.J. Department of Mechanical Engineering Center for Computational Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States

Data-driven, deep-learning modeling frameworks have been recently developed for forecasting time series data. Such machine learning models may be useful in multiple domains including the atmospheric and oceanic ones, and in general, the larger fluids community. The present work investigates the possible effectiveness of such deep neural operator models for reproducing and predicting classic fluid flows and simulations of realistic ocean dynamics. We first briefly evaluate the capabilities of such deep neural operator models when trained on a simulated two-dimensional fluid flow past a cylinder. We then investigate their application to forecasting ocean surface circulation in the Middle Atlantic Bight and Massachusetts Bay, learning from high-resolution data-assimilative simulations employed for real sea experiments. We confirm that trained deep neural operator models are capable of predicting idealized periodic eddy shedding. For realistic ocean surface flows and our preliminary study, they can predict several of the features and show some skill, providing potential for future research and *** Codes 76U60, 86A05, 86-08, 86A10, 86A08, 68T01, 68T07, 68T37 © 2023, CC BY-NC-ND.

关键词： Flow of fluids

Attention weights accurately predict language representations in the brain

学校读者我要写书评

暂无评论

Attention weights accurately predict language representation...

2022 Findings of the Association for computational Linguistics: EMNLP 2022

作者： Lamarre, Mathis Chen, Catherine Deniz, Fatma Institute of Software Engineering and Theoretical Computer Science Technische Universität Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Helen Wills Neuroscience Institute University of California Berkeley United States

In Transformer-based language models (LMs) the attention mechanism converts token embeddings into contextual embeddings that incorporate information from neighboring words. The resulting contextual hidden state embeddings have enabled highly accurate models of brain responses, suggesting that the attention mechanism constructs contextual embeddings that carry information reflected in language-related brain representations. However, it is unclear whether the attention weights that are used to integrate information across words are themselves related to language representations in the brain. To address this question we analyzed functional magnetic resonance imaging (fMRI) recordings of participants reading English language narratives. We provided the narrative text as input to two LMs (BERT and GPT-2) and extracted their corresponding attention weights. We then used encoding models to determine how well attention weights can predict recorded brain responses. We find that attention weights accurately predict brain responses in much of the frontal and temporal cortices. Our results suggest that the attention mechanism itself carries information that is reflected in brain representations. Moreover, these results indicate cortical areas in which context integration may occur. © 2022 Association for computational Linguistics.

关键词： Brain

3D Vessel Graph Generation Using Denoising Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Prabhakar, Chinmay Shit, Suprosanna Musio, Fabio Yang, Kaiyuan Amiranashvili, Tamaz Paetzold, Johannes C. Li, Hongwei Bran Menze, Bjoern Department of Quantitative Biomedicine University of Zurich Switzerland Center for Computational Health ZHAW Switzerland Department of Computer Science Technical University of Munich Germany Department of Computing Imperial College London United Kingdom Athinoula A. Martinos Center Harvard Medical School United States

Blood vessel networks, represented as 3D graphs, help predict disease biomarkers, simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre-clinical settings. However, generating realistic vessel graphs that correspond to an anatomy of interest is challenging. Previous methods aimed at generating vessel trees mostly in an autoregressive style and could not be applied to vessel graphs with cycles such as capillaries or specific anatomical structures such as the Circle of Willis. Addressing this gap, we introduce the first application of denoising diffusion models in 3D vessel graph generation. Our contributions include a novel, two-stage generation method that sequentially denoises node coordinates and edges. We experiment with two real-world vessel datasets, consisting of microscopic capillaries and major cerebral vessels, and demonstrate the generalizability of our method for producing diverse, novel, and anatomically plausible vessel graphs. © 2024, CC BY.

关键词： Blood vessels

Hypercomplex Generative Adversarial Networks for Lightweight Semantic Labeling 3rd

学校读者我要写书评

暂无评论

Hypercomplex Generative Adversarial Networks for Lightweigh...

3rd International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2022

作者： Sfikas, Giorgos Retsinas, George Gatos, Basilis Nikou, Christophoros Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Center for Scientific Research "Demokritos" Athens Greece School of Electrical and Computer Engineering National Technical University of Athens Athens Greece Department of Surveying and Geoinformatics Engineering University of West Attica Athens Greece Department of Computer Science and Engineering University of Ioannina Ioannina Greece

ISBN: (纸本)9783031090363

Following recent advances on parameterized hypercomplex multiplication [21], we explore the usefulness of hypercomplex convolutions and deconvolutions in a document labeling task. We show that the proposed Hypercomplex Generative Adversarial Networks achieve excellent results while requiring significantly less independent parameters than real-valued models. © 2022, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

BetaExplainer: A Probabilistic Method to Explain Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sloneker, Whitney Patel, Shalin Wang, Michael Crawford, Lorin Singh, Ritambhara Center for Computational Molecular Biology Brown University ProvidenceRI United States Department of Computer Science Brown University ProvidenceRI United States Microsoft Research CambridgeMA United States

Graph neural networks (GNNs) are powerful tools for conducting inference on graph data but are often seen as"black boxes" due to difficulty in extracting meaningful subnetworks driving predictive performance. Many interpretable GNN methods exist, but they cannot quantify uncertainty in edge weights and suffer in predictive accuracy when applied to challenging graph structures. In this work, we proposed BetaExplainer which addresses these issues by using a sparsity-inducing prior to mask unimportant edges during model training. To evaluate our approach, we examine various simulated data sets with diverse real-world characteristics. Not only does this implementation provide a notion of edge importance uncertainty, it also improves upon evaluation metrics for challenging datasets compared to state-of-the art explainer methods. © 2024, CC BY.

关键词： Neural network models

Identifying Novel Drug Targets by iDTPnd:A Case Study of Kinase Inhibitors

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2021年第6期19卷 986-997页

作者： Hammad Naveed Corinna Reglin Thomas Schubert Xin Gao Stefan T.Arold Michael L.Maitland Toyota Technological Institute at Chicago ChicagoIL 60637USA Department of Computer Science National University of Computer and Emerging SciencesIslamabad 44000Pakistan 2bind GmbH D-93053 RegensburgGermany King Abdullah University of Science and Technology(KAUST) Computational Bioscience Research Center(CBRC)ComputerElectrical and Mathematical Sciences and Engineering(CEMSE)DivisionThuwal 23955Saudi Arabia King Abdullah University of Science and Technology(KAUST) Computational Bioscience Research Center(CBRC)Biological and Environmental Sciences and Engineering(BESE)DivisionThuwal 23955Saudi Arabia Inova Center for Personalized Health and Schar Cancer Institute Falls ChurchVA 22042USA University of Virginia Cancer Center AnnandaleVA 22003USA

Current FDA-approved kinase inhibitors cause diverse adverse effects,some of which are due to the me-chanism-independent effects of these *** these mechanism-independent interactions could improve drug safety and support drug ***,we develop iDTPnd(integrated Drug Target Predictor with negative dataset),a computational approach for large-scale discovery of novel targets for known *** a given drug,we construct a positive structural signature as well as a negative structural signature that captures the weakly conserved structural features of drug-binding *** facilitate assessment of unintended targets,iDTPnd also provides a docking-based interaction score and its statistical *** confirm the interactions of sorafenib,imatinib,dasatinib,sunitinib,and pazopanib with their known targets at a sensitivity of 52%and a specificity of 55%.We also validate 10 predicted novel targets by using in vitro *** results suggest that proteins other than kinases,such as nuclear receptors,cytochrome P450,and MHC class I molecules,can also be physiologically relevant targets of kinase *** method is general and broadly applicable for the identification of protein–small molecule interactions,when sufficient drug–target 3D data are *** code for constructing the structural signatures is available at https://***/Documents/***.

关键词： Protein-drug interaction iDTPnd Kinase inhibitor Drug-binding site signature Drug repurposing

The computational Curse of Big Data for Bayesian Additive Regression Trees: A Hitting Time Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tan, Yan Shuo Ronen, Omer Saarinen, Theo Yu, Bin Department of Statistics and Data Science National University of Singapore Singapore Department of Statistics UC Berkeley United States Department of Electrical Engineering and Computer Sciences UC Berkeley United States Center for Computational Biology UC Berkeley United States

Bayesian Additive Regression Trees (BART) is a popular Bayesian non-parametric regression model that is commonly used in causal inference and beyond. Its strong predictive performance is supported by theoretical guarantees that its posterior distribution concentrates around the true regression function at optimal rates under various data generative settings and for appropriate prior choices. In this paper, we show that the BART sampler often converges slowly, confirming empirical observations by other researchers. Assuming discrete covariates, we show that, while the BART posterior concentrates on a set comprising all optimal tree structures (smallest bias and complexity), the Markov chain's hitting time for this set increases with n (training sample size), under several common data generative settings. As n increases, the approximate BART posterior thus becomes increasingly different from the exact posterior (for the same number of MCMC samples), contrasting with earlier concentration results on the exact posterior. This contrast is highlighted by our simulations showing worsening frequentist undercoverage for approximate posterior intervals and a growing ratio between the MSE of the approximate posterior and that obtainable by artificially improving convergence via averaging multiple sampler chains. Finally, based on our theoretical insights, possibilities are discussed to improve the BART sampler convergence *** Codes 62G08, 65C40 © 2024, CC BY.

关键词： Big data