检索结果-内蒙古大学图书馆

XCrossNet: Feature structure-oriented learning for click-through rate prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Runlong Ye, Yuyang Liu, Qi Wang, Zihan Yang, Chunfeng Hu, Yucheng Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Management Science and Information Systems Rutgers Business School Rutgers University Newark United States MOE Key Laboratory of Computational Linguistics School of Electronics Engineering and Computer Science Peking University Beijing China Tencent Inc Shenzhen China

Click-Through Rate (CTR) prediction is a core task in nowadays commercial recommender systems. Feature crossing, as the mainline of research on CTR prediction, has shown a promising way to enhance predictive performance. Even though various models are able to learn feature interactions without manual feature engineering, they rarely attempt to individually learn representations for different feature structures. In particular, they mainly focus on the modeling of cross sparse features but neglect to specifically represent cross dense features. Motivated by this, we propose a novel Extreme Cross Network, abbreviated XCrossNet, which aims at learning dense and sparse feature interactions in an explicit manner. XCrossNet as a feature structure-oriented model leads to a more expressive representation and a more precise CTR prediction, which is not only explicit and interpretable, but also time-efficient and easy to implement. Experimental studies on Criteo Kaggle dataset show significant improvement of XCrossNet over state-of-the-art models on both effectiveness and efficiency. © 2021, CC BY.

关键词： Forecasting

Analysis of machine learning strategies for prediction of passing undergraduate admission test

学校读者我要写书评

暂无评论

International Journal of Information Management data Insights 2022年第2期2卷

作者： Walid, Md. Abul Ala Ahmed, S.M. Masum Zeyad, Mohammad Galib, S. M. Saklain Nesa, Meherun Department of Computer Science and Engineering Bangabandhu Sheikh Mujibur Rahman Science and Technology University (BSMRSTU) Gopalganj 8100 Bangladesh Department of Computer Science and Engineering Khulna University of Engineering and Technology (KUET) Khulna 9203 Bangladesh Energy and Technology Research Division Advanced Bioinformatics Computational Biology and Data Science Laboratory Bangladesh (ABCD Laboratory Bangladesh) Chattogram 4226 Bangladesh Faculty of Engineering University of Mons (UMONS) Bd Dolez 31 Mons 7000 Belgium School of Engineering and Physical Sciences (EPS) Heriot-Watt University (HWU) EH14 4AS Scotland Edinburgh United Kingdom Department of Energy Engineering University of the Basque Country (UPV/EHU) Ingeniero Torres Quevedo Plaza 1 Biscay Bilbao 48013 Spain School of Science & Technology International Hellenic University (IHU) 14th km Thessaloniki – N. Moudania Thessaloniki Thermi 57001 Greece Department of Biomedical Engineering Khulna University of Engineering and Technology (KUET) Khulna 9203 Bangladesh

This article primarily focuses on understanding the reasons behind the failure of undergraduate admission seekers using different machine learning (ML) strategies. An operative dataset has been equipped using the least significant attributes to avoid the complexity of the model. The procedure halted after obtaining 343 observations with ten different attributes. The predictions are achieved using six immensely used ML techniques. Stratified K-fold cross-validation is mentioned to measure the expertise of proposed models to unsighted data, and Precision, Recall, F-Measure, and AUC Score matrices are determined to assess the efficiency of each model. A comprehensive investigation of this article indicates that the resampling strategy derived from the combination of edited nearest neighbor (ENN) and borderline SVM-based SMOTE and SVM model achieved prominent performance. Additionally, the borderline SVM-based SMOTE and the Adaboost model performs as the second-highest performing model. © 2022 The Author(s)

关键词： Adaboost Balanced dataset Machine Learning Precision Support Vector Machines (SVM)

14 Examples of How LLMs Can Transform Materials science and Chemistry: A Reflection on a Large Language Model Hackathon

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jablonka, Kevin Maik Ai, Qianxiang Al-Feghali, Alexander Badhwar, Shruti Bocarsly, Joshua D. Bran, Andres M. Bringuier, Stefan Brinson, L. Catherine Choudhary, Kamal Circi, Defne Cox, Sam de Jong, Wibe A. Evans, Matthew L. Gastellu, Nicolas Genzling, Jerome Gil, María Victoria Gupta, Ankur K. Hong, Zhi Imran, Alishba Kruschwitz, Sabine Labarre, Anne Lála, Jakub Liu, Tao Ma, Steven Majumdar, Sauradeep Merz, Garrett W. Moitessier, Nicolas Moubarak, Elias Mouriño, Beatriz Pelkie, Brenden Pieler, Michael Ramos, Mayk Caldas Ranković, Bojana Rodriques, Samuel G. Sanders, Jacob N. Schwaller, Philippe Schwarting, Marcus Shi, Jiale Smit, Berend Smith, Ben E. Van Herck, Joren Völker, Christoph Ward, Logan Warren, Sean Weiser, Benjamin Zhang, Sylvester Zhang, Xiaoqi Zia, Ghezal Ahmad Scourtas, Aristana Schmidt, K.J. Foster, Ian White, Andrew D. Blaiszik, Ben Sion Valais Switzerland Department of Chemical Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Department of Chemistry McGill University MontrealQC Canada Reincarnate Inc. United States Yusuf Hamied Department of Chemistry University of Cambridge Lensfield Road CambridgeCB2 1EW United Kingdom Lausanne Switzerland Lausanne Switzerland San Diego CA United States Mechanical Engineering and Materials Science Duke University United States Material Measurement Laboratory National Institute of Standards and Technology MD20899 United States Department of Chemical Engineering University of Rochester United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory BerkeleyCA94720 United States UCLouvain Chemin des Étoiles 8 Louvain-la-Neuve1348 Belgium Matgenix SRL 185 Rue Armand Bury Gozée 6534 Belgium CSIC Francisco Pintado Fe 26 Oviedo33011 Spain Department of Computer Science University of Chicago ChicagoIL60637 United States Computer Science University of California Berkeley BerkeleyCA94704 United States Bundesanstalt für Materialforschung und -Prüfung Unter den Eichen 87 Berlin12205 Germany Francis Crick Institute 1 Midland Rd LondonNW1 1AT United Kingdom American Family Insurance Data Science Institute University of Wisconsin-Madison MadisonWI53706 United States Department of Chemical Engineering University of Washington SeattleWA98105 United States *** Stability.AI United Kingdom Department of Chemistry and Biochemistry University of California Los AngelesCA90095 United States Department of Computer Science University of Chicago ChicagoIL60490 United States Data Science and Learning Division Argonne National Lab United States Globus University of Chicago Data Science and Learning Division Argonne National Lab United States Department of Computer Science University of Chicago Data Science and Learning Division Argonne National Lab United

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines. © 2023, CC BY.

关键词： computational linguistics

TARGET SPECIFIC DE NOVO DESIGN OF DRUG CANDIDATE MOLECULES WITH GRAPH TRANSFORMER-BASED GENERATIVE ADVERSARIAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ünlü, Atabey Çevrim, Elif Sarıgün, Ahmet Yiğit, Melih Gökay Çelikbilek, Hayriye Bayram, Osman Güvenilir, Heval Ataş Koyaş, Altay Kahraman, Deniz Cansen Olğaç, Abdurrahman Rifaioğlu, Ahmet Banoğlu, Erden Doğan, Tunca Biological Data Science Lab Dept. of Computer Engineering Hacettepe University Turkey Dept. of Bioinformatics Graduate School of Health Sciences Hacettepe University Turkey Dept. of Chemistry Middle East Technical University Turkey Dept. of Physics Middle East Technical University Turkey Dept. of Computer Engineering Middle East Technical University Turkey Dept. Of Artificial Intelligence Engineering Bahcesehir University Turkey Cancer Systems Biology Lab Graduate School of Informatics Middle East Technical University Turkey Dept. of Pharmaceutical Chemistry Faculty of Pharmacy Gazi University Turkey Laboratory of Molecular Modeling Evias Pharmaceutical R&D Ltd Turkey Dept. of Electrical and Electronics Engineering Iskenderun Technical University Turkey Institute for Computational Biomedicine Heidelberg University Germany

Discovering novel drug candidate molecules is one of the most fundamental and critical steps in drug development. Generative deep learning models, which create synthetic data given a probability distribution, offer a high potential for designing de novo molecules. However, for them to be useful in real-life drug development pipelines, these models should be able to design drug-like and target-centric molecules. In this study, we propose an end-to-end generative system, DrugGEN, for the de novo design of drug candidate molecules that interact with intended target proteins. The proposed method represents molecules as graphs and processes them via a generative adversarial network comprising graph transformer layers. The system is trained using a large dataset of drug-like compounds and target-specific bioactive molecules to design effective inhibitory molecules against the AKT1 protein, which is critically important in developing treatments for various types of cancer. We conducted molecular docking and dynamics to assess the target-centric generation performance of the model, as well as attention score visualisation to examine model interpretability. Results indicate that our de novo molecules have a high potential for interacting with the AKT1 protein at the level of its native ligands. Using the open-access DrugGEN codebase, it is possible to easily train models for other druggable proteins, given a dataset of experimentally known bioactive molecules. © 2023, CC BY-NC-SA.

关键词： Generative adversarial networks

Spatiotemporal Image Reconstruction to Enable High-Frame Rate Dynamic Photoacoustic Tomography with Rotating-Gantry Volumetric Imagers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cam, Refik Mert Wang, Chao Thompson, Weylan Ermilov, Sergey A. Anastasio, Mark A. Villa, Umberto University of Illinois Urbana-Champaign Department of Electrical & Computer Engineering 306 North Wright Street UrbanaIL61801 United States Department of Statistics and Data Science National University of Singapore Singapore PhotoSound Technologies Inc. HoustonTX77036 United States University of Illinois Urbana-Champaign Department of Bioengineering 1406 West Green Street UrbanaIL61801 United States The University of Texas at Austin Oden Institute for Computational Engineering & Sciences 201 East 24th Street AustinTX78712 United States

Significance: Dynamic photoacoustic computed tomography (PACT) is a valuable imaging technique for monitoring physiological processes. However, current dynamic PACT imaging techniques are often limited to two-dimensional (2D) spatial imaging. While volumetric PACT imagers are commercially available, these systems typically employ a rotating measurement gantry in which the tomographic data are sequentially acquired, as opposed to being acquired simultaneously at all views. Because the dynamic object varies during the data-acquisition process, the sequential data-acquisition process poses substantial challenges to image reconstruction associated with data incompleteness. The proposed image reconstruction method is highly significant in that it will address these challenges and enable volumetric dynamic PACT imaging with existing preclinical imagers. Aim: The aim of this study is to develop a spatiotemporal image reconstruction method for dynamic PACT that can be applied to commercially available volumetric PACT imagers that employ a sequential scanning strategy. The proposed reconstruction method aims to overcome the challenges caused by the limited number of tomographic measurements acquired per frame. Approach: A low-rank matrix estimation-based spatiotemporal image reconstruction method (LRME-STIR) is proposed to enable dynamic volumetric PACT. The LRME-STIR method leverages the spatiotemporal redundancies in the dynamic object to accurately reconstruct a four-dimensional (4D) spatiotemporal image. Results: The conducted numerical studies substantiate the LRME-STIR method’s efficacy in reconstructing 4D dynamic images from tomographic measurements acquired with a rotating measurement gantry. The experimental study demonstrates the method’s ability to faithfully recover the flow of a contrast agent at a frame rate of 0.1 seconds, even when only a single tomographic measurement per frame is available. Conclusions: The proposed LRME-STIR method offers a promising solu

关键词： Image reconstruction

Unsupervised many-to-many stain translation for histological image augmentation to improve classification accuracy

学校读者我要写书评

暂无评论

Journal of Pathology Informatics 2023年 14卷 100195-100195页

作者： Berijanian, Maryam Schaadt, Nadine S. Huang, Boqiang Lotz, Johannes Feuerhake, Friedrich Merhof, Dorit Department of Computational Mathematics Science and Engineering (CMSE) Michigan State University East Lansing United States Institute for Pathology Hannover Medical School Hannover Germany Institute of Image Analysis and Computer Vision Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Lübeck Germany Institute for Neuropathology University Clinic Freiburg Freiburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Background: Deep learning tasks, which require large numbers of images, are widely applied in digital pathology. This poses challenges especially for supervised tasks since manual image annotation is an expensive and laborious process. This situation deteriorates even more in the case of a large variability of images. Coping with this problem requires methods such as image augmentation and synthetic image generation. In this regard, unsupervised stain translation via GANs has gained much attention recently, but a separate network must be trained for each pair of source and target domains. This work enables unsupervised many-to-many translation of histopathological stains with a single network while seeking to maintain the shape and structure of the tissues. Methods: StarGAN-v2 is adapted for unsupervised many-to-many stain translation of histopathology images of breast tissues. An edge detector is incorporated to motivate the network to maintain the shape and structure of the tissues and to have an edge-preserving translation. Additionally, a subjective test is conducted on medical and technical experts in the field of digital pathology to evaluate the quality of generated images and to verify that they are indistinguishable from real images. As a proof of concept, breast cancer classifiers are trained with and without the generated images to quantify the effect of image augmentation using the synthetized images on classification accuracy. Results: The results show that adding an edge detector helps to improve the quality of translated images and to preserve the general structure of tissues. Quality control and subjective tests on our medical and technical experts show that the real and artificial images cannot be distinguished, thereby confirming that the synthetic images are technically plausible. Moreover, this research shows that, by augmenting the training dataset with the outputs of the proposed stain translation method, the accuracy of breast cancer classifie

关键词： Adversarial networks Breast cancer classifier Deep learning Digital pathology Stain translation Unsupervised

Biases in Inverse Ising Estimates of Near-Critical Behaviour

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kloucek, Maximilian B. Machon, Thomas Kajimura, Shogo Royall, C. Patrick Masuda, Naoki Turci, Francesco H.H. Wills Laboratory School of Physics University of Bristol Bristol United Kingdom Bristol Centre for Functional Nanomaterials University of Bristol Bristol United Kingdom Faculty of Information and Human Sciences Kyoto Institute of Technology Kyoto606-8585 Japan Gulliver UMR CNRS 7083 ESPCI Paris Université PSL Paris75005 France Department of Mathematics State University of New York BuffaloNY14260-2900 United States Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY14260-5030 United States

Inverse Ising inference allows pairwise interactions of complex binary systems to be reconstructed from empirical correlations. Typical estimators used for this inference, such as Pseudo-likelihood maximization (PLM), are biased. Using the Sherrington-Kirkpatrick (SK) model as a benchmark, we show that these biases are large in critical regimes close to phase boundaries, and may alter the qualitative interpretation of the inferred model. In particular, we show that the small-sample bias causes models inferred through PLM to appear closer-to-criticality than one would expect from the data. data-driven methods to correct this bias are explored and applied to a functional magnetic resonance imaging (fMRI) dataset from neuroscience. Our results indicate that additional care should be taken when attributing criticality to real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Criticality (nuclear fission)

Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Sibo Quilodrán-Casas, César Ouala, Said Farchi, Alban Liu, Che Tandeo, Pierre Fablet, Ronan Lucor, Didier Iooss, Bertrand Brajard, Julien Xiao, Dunhui Janjic, Tijana Ding, Weiping Guo, Yike Carrassi, Alberto Bocquet, Marc Arcucci, Rossella Data Science Institute Department of Computing Imperial College London LondonSW7 2AZ United Kingdom Department of Earth Science and Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong IMT Atlantique Lab-STICC UMR CNRS 6285 France and Odyssey Inria/IMT France RIKEN Center for Computational Science Kobe Japan CEREA École des Ponts and EDF R&D île-de-France France The Laboratoire Interdisciplinaire des Sciences du Numérique CNRS Paris-Saclay University OrsayF-91403 France 78401 Chatou France Institut de Mathématiques de Toulouse Toulouse31062 France SINCLAIR AI Lab Saclay France Bergen Norway School of Mathematical Sciences Tongji University Shanghai200092 China Mathematical Institute for Machine Learning and Data Science KU Eichstätt-Ingolstadt Bavaria Germany School of Information Science and Technology Nantong University Nantong226019 China Department of Physics and Astronomy Augusto Righi University of Bologna Bologna40124 Italy

data Assimilation (DA) and Uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and climate systems. Recently, much effort has been given in combining DA, UQ and machine learning (ML) techniques. These research efforts seek to address some critical challenges in high-dimensional dynamical systems, including but not limited to dynamical system identification, reduced order surrogate modelling, error covariance specification and model error correction. A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains, resulting in the necessity for a comprehensive guide. This paper provides the first overview of the state-of-the-art researches in this interdisciplinary field, covering a wide range of applications. This review aims at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models, but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems. Therefore, this article has a special focus on how ML methods can overcome the existing limits of DA and UQ, and vice versa. Some exciting perspectives of this rapidly developing research field are also discussed. © 2023, CC BY-NC-SA.

关键词： Dynamical systems

A Two-Stage Approach for Segmenting Spatial Point Patterns Applied to Multiplex Imaging

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sheng, Alvin Reich, Brian J. Staicu, Ana-Maria Krishnan, Santhoshi N. Rao, Arvind Frankel, Timothy L. Division of Biostatistics and Health Data Science University of Minnesota MinneapolisMN United States Department of Statistics North Carolina State University RaleighNC United States Department of Computational Medicine and Bioinformatics University of Michigan Ann ArborMI United States Department of Electrical and Computer Engineering Rice University HoustonTX United States Department of Biostatistics University of Michigan Ann ArborMI United States Department of Radiation Oncology University of Michigan Ann ArborMI United States Department of Biomedical Engineering University of Michigan Ann ArborMI United States Department of Surgery University of Michigan Ann ArborMI United States

Recent advances in multiplex imaging have enabled researchers to locate different types of cells within a tissue sample. This is especially relevant for tumor immunology, as clinical regimes corresponding to different stages of disease or responses to treatment may manifest as different spatial arrangements of tumor and immune cells. Spatial point pattern modeling can be used to partition multiplex tissue images according to these regimes. To this end, we propose a two-stage approach: first, local intensities and pair correlation functions are estimated from the spatial point pattern of cells within each image, and the pair correlation functions are reduced in dimension via spectral decomposition of the covariance function. Second, the estimates are clustered in a Bayesian hierarchical model with spatially-dependent cluster labels. The clusters correspond to regimes of interest that are present across subjects;the cluster labels segment the spatial point patterns according to those regimes. Through Markov Chain Monte Carlo sampling, we jointly estimate and quantify uncertainty in the cluster assignment and spatial characteristics of each cluster. Simulations demonstrate the performance of the method, and it is applied to a set of multiplex immunofluorescence images of diseased pancreatic tissue. Copyright © 2024, The Authors. All rights reserved.

关键词： Tumors