Search Results - active learning large deviations perceptron model message-passing algorithms*

Large deviations in the perceptron model and consequences for active learning

Authors: Cui, Hugo Saglietti, Luca Zdeborovà, Lenka et al.

Contributors: Cui, Hugo Saglietti, Luca Zdeborovà, Lenka et al.

Source: Machine Learning: Science and Technology

Subject Terms: FOS: Computer and information sciences, 0301 basic medicine, ACTIVE LEARNING, LARGE DEVIATIONS, PERCEPTRON MODEL, MESSAGE-PASSING ALGORITHMS, Computer Science - Machine Learning, Active learning, Large Deviations, Active learning Large Deviations Perceptron Model Message-passing algorithms, FOS: Physical sciences, PERCEPTRON MODEL, LARGE DEVIATIONS, ACTIVE LEARNING, Disordered Systems and Neural Networks (cond-mat.dis-nn), Condensed Matter - Disordered Systems and Neural Networks, Perceptron Model, Message-passing algorithms, 01 natural sciences, [PHYS] Physics [physics], Machine Learning (cs.LG), 03 medical and health sciences, 0103 physical sciences

File Description: application/pdf

Access URL: http://arxiv.org/abs/1912.03927
https://cea.hal.science/cea-04542510v1
https://cea.hal.science/cea-04542510v1/document
https://doi.org/10.1088/2632-2153/abfbbb
https://iopscience.iop.org/article/10.1088/2632-2153/abfbbb
https://proceedings.mlr.press/v107/cui20a.html
https://hdl.handle.net/11565/4046568
https://hdl.handle.net/11565/4046563
https://doi.org/10.1088/2632-2153/abfbbb
https://iopscience.iop.org/article/10.1088/2632-2153/abfbbb

Large deviations for the perceptron model and consequences for active learning

Authors: Cui, Hugo Saglietti, Luca Zdeborova, Lenka

Contributors: Cui, Hugo Saglietti, Luca Zdeborova, Lenka

Subject Terms: ACTIVE LEARNING, LARGE DEVIATIONS, PERCEPTRON MODEL, MESSAGE-PASSING ALGORITHMS

File Description: ELETTRONICO

Relation: info:eu-repo/semantics/altIdentifier/wos/WOS:001234508200018; ispartofbook:Proceedings of Machine Learning Research. Vol. 107: Mathematical and Scientific Machine Learning, 20-24 July 2020, Princeton University, Princeton, NJ, USA; Mathematical and Scientific Machine Learning; numberofpages:41; serie:PROCEEDINGS OF MACHINE LEARNING RESEARCH; http://hdl.handle.net/11565/4046568; https://proceedings.mlr.press/v107/cui20a.html

Availability: http://hdl.handle.net/11565/4046568
https://proceedings.mlr.press/v107/cui20a.html

Large deviations for the perceptron model and consequences for active learning

Authors: Cui, Hugo Saglietti, Luca Zdeborová, Lenka

Index Terms: Condensed Matter - Disordered Systems and Neural Networks, Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/1912.03927

Towards interpretable drug interaction prediction via dual-stage attention and Bayesian calibration with active learning.

Authors: Li, Rongpei Zhang, Yufang Sun, Heqi et al.

Source: PeerJ Computer Science; Apr2025, p1-32, 32p

Subject Terms: DRUG interactions, ACTIVE learning, DRUG side effects, PHARMACOLOGY, RECURRENT neural networks, BAYESIAN analysis

Smart distributed data factory volunteer computing platform for active learning-driven molecular data acquisition.

Authors: Ghukasyan, Tsolak Altunyan, Vahagn Bughdaryan, Aram et al.

Source: Scientific Reports; 2/28/2025, Vol. 15 Issue 1, p1-14, 14p

Subject Terms: GRAPH neural networks, MACHINE learning, MOLECULAR conformation, PHYSICAL & theoretical chemistry, COMPUTATIONAL chemistry

Deep ensembles vs committees for uncertainty estimation in neural-network force fields: Comparison and application to active learning.

Authors: Carrete, Jesús Montes-Campos, Hadrián Wanzenböck, Ralf et al.

Source: Journal of Chemical Physics; 5/28/2023, Vol. 158 Issue 20, p1-18, 18p

Subject Terms: ACTIVE learning, LIQUID surfaces, MACHINE learning, FORCE & energy, IONIC liquids

Accelerating crystal structure search through active learning with neural networks for rapid relaxations.

Authors: Hessmann, Stefaan S. P. Schütt, Kristof T. Gebauer, Niklas W. A. et al.

Source: NPJ Computational Materials; 2/20/2025, Vol. 11 Issue 1, p1-11, 11p

Subject Terms: DENSITY functional theory, CHEMICAL structure, GLOBAL optimization, CRYSTAL structure, CRYSTALS

Generating Activity Snippets by Learning Human-Scene Interactions.

Authors: Li, Changyang Yu, Lap-Fai

Source: ACM Transactions on Graphics; Aug2023, Vol. 42 Issue 4, p1-15, 15p

Subject Terms: ACTIVE learning, VIRTUAL reality, POSE estimation (Computer vision), GRAPH algorithms

Physics-informed graph neural networks enhance scalability of variational nonequilibrium optimal control.

Authors: Yan, Jiawei Rotskoff, Grant M.

Source: Journal of Chemical Physics; 8/21/2022, Vol. 157 Issue 7, p1-12, 12p

Subject Terms: NONEQUILIBRIUM statistical mechanics, DISTRIBUTION (Probability theory), SCALABILITY, GENERATING functions, LARGE deviations (Mathematics), STATISTICAL mechanics

ALReg: Registration of 3D Point Clouds Using Active Learning.

Authors: Sahin, Yusuf Huseyin Karabacak, Oguzhan Kandemir, Melih et al.

Source: Applied Sciences (2076-3417); Jul2023, Vol. 13 Issue 13, p7422, 15p

Subject Terms: DEEP learning, POINT cloud, ACTIVE learning, CLOUD computing, RECORDING & registration

Calibrated geometric deep learning improves kinase–drug binding predictions.

Authors: Luo, Yunan Liu, Yang Peng, Jian

Source: Nature Machine Intelligence; Dec2023, Vol. 5 Issue 12, p1390-1401, 12p

A deep-learning approach to predict reproductive toxicity of chemicals using communicative message passing neural network.

Authors: He, Owen Chen, Daoxing Li, Yimei

Source: Frontiers in Toxicology; 2025, p1-12, 12p

Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks.

Authors: Ünlü, Atabey Çevrim, Elif Yiğit, Melih Gökay et al.

Source: Nature Machine Intelligence; Sep2025, Vol. 7 Issue 9, p1524-1540, 17p

Comprehensive review of machine learning and deep learning techniques for epileptic seizure detection and prediction based on neuroimaging modalities.

Authors: Slama, Khadija Yahyaouy, Ali Riffi, Jamal et al.

Source: Visual Computing for Industry, Biomedicine & Art; 12/11/2025, Vol. 8 Issue 1, p1-37, 37p

SAGEFusionNet: An Auxiliary Supervised Graph Neural Network for Brain Age Prediction as a Neurodegenerative Biomarker.

Authors: Kumar, Suraj Hazarika, Suman Gupta, Cota Navin

Source: Brain Sciences (2076-3425); Jul2025, Vol. 15 Issue 7, p752, 19p

Subject Terms: GRAPH neural networks, PARKINSON'S disease, NEURODEGENERATION, MODEL validation, MAGNETIC resonance imaging, DATA fusion (Statistics), AGE factors in cognition

Tailored structured peptide design with a key-cutting machine approach.

Authors: Leyva, Yan C. Torres, Marcelo D. T. Oliva, Carlos A. et al.

Source: Nature Machine Intelligence; Oct2025, Vol. 7 Issue 10, p1685-1697, 13p

Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol.

Authors: Li, Mingyu Song, Kun He, Jixiao et al.

Source: Nature Machine Intelligence; Aug2025, Vol. 7 Issue 8, p1355-1368, 14p

State-specific protein–ligand complex structure prediction with a multiscale deep generative model.

Authors: Qiao, Zhuoran Nie, Weili Vahdat, Arash et al.

Source: Nature Machine Intelligence; Feb2024, Vol. 6 Issue 2, p195-208, 14p

Discovery, design, and engineering of enzymes based on molecular retrobiosynthesis.

Authors: Chen, Ancheng Peng, Xiangda Shen, Tao et al.

Source: mLife; Apr2025, Vol. 4 Issue 2, p107-125, 19p

PocketFlow is a data-and-knowledge-driven structure-based molecular generative model.

Authors: Jiang, Yuanyuan Zhang, Guo You, Jing et al.

Source: Nature Machine Intelligence; Mar2024, Vol. 6 Issue 3, p326-337, 12p