检索结果-内蒙古大学图书馆

The leave-one-covariate-out conditional randomization test

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Katsevich, Eugene Ramdas, Aaditya Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University

Conditional independence testing is an important problem, yet provably hard without assumptions. One of the assumptions that has become popular of late is called "model-X", where we assume we know the joint distribution of the covariates, but assume nothing about the conditional distribution of the outcome given the covariates. Knockoffs is a popular methodology associated with this framework, but it suffers from two main drawbacks: only one-bit p-values are available for inference on each variable, and the method is randomized with significant variability across runs in practice. The conditional randomization test (CRT) is thought to be the "right" solution under model-X, but usually viewed as computationally inefficient. This paper proposes a computationally efficient leave-one-covariate-out (LOCO) CRT that addresses both drawbacks of knockoffs. LOCO CRT produces valid p-values that can be used to control the familywise error rate, and has nearly zero algorithmic variability. For L1 regularized M-estimators, we develop an even faster variant called L1ME CRT, which reuses computation by leveraging a novel observation about the stability of the cross-validated lasso to removing inactive variables. Last, for multivariate Gaussian covariates, we present a closed form expression for the LOCO CRT p-value, thus completely eliminating resampling in this important special case. Copyright © 2020, The Authors. All rights reserved.

关键词： Random processes

T-Cell Receptor Optimization with Reinforcement learning and Mutation Polices for Precision Immunotherapy 27th

学校读者我要写书评

暂无评论

T-Cell Receptor Optimization with Reinforcement Learning an...

27th International Conference on Research in Computational Molecular Biology, RECOMB 2023

作者： Chen, Ziqi Min, Martin Renqiang Guo, Hongyu Cheng, Chao Clancy, Trevor Ning, Xia Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Machine Learning Department NEC Labs PrincetonNJ08540 United States Digital Technologies Research Centre National Research Council Canada Ontario Canada Department of Medicine Baylor College of Medicine HoustonTX77030 United States NEC Oncolmmunity AS Oslo Cancer Cluster Innovation Park Ullernchausséen 64 Oslo0379 Norway Biomedical Informatics The Ohio State University ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

ISBN: (纸本)9783031291180

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (Formula Presented) problem, and presented a framework (Formula Presented) with a mutation policy using proximal policy optimization. (Formula Presented) mutates TCRs into effective ones that can recognize given peptides. (Formula Presented) leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared (Formula Presented) with multiple baseline methods and demonstrated that (Formula Presented) significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of(Formula Presented) for both precision immunotherapy and peptide-recognizing TCR motif discovery. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement learning

Condition Monitoring and Fault Diagnosis of BLDC Motor in Electric Vehicles Using Artificial Intelligence

学校读者我要写书评

暂无评论

Condition Monitoring and Fault Diagnosis of BLDC Motor in El...

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Swapnil Gundewar Meher Langote Swapna Kamble Prashant Kamble Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Maharashtra India Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Maharashtra India Department of Information Technology Yeshwantrao Chavan College of Engineering Nagpur Maharashtra India Department of Mechanical Technology Yeshwantrao Chavan College of Engineering Nagpur Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

Due to their high benefits in terms of environment and standards of battery advancement, Electric Vehicles (EVs) are extremely important in the shift towards transportation. Here the Brushless DC (BLDC) motor is an integrated part of the EVs, and it has become the most popular choice due to better efficiency, reliability, and reduced maintenance requirements than the others. The major difference from traditional motors is that BLDC motors make use of electronic commutation, so brushes are not employed; this results in lower amounts of wear. This not only helps the motor to have a longer working life but also to work more efficiently, or to maintain their efficiency. However, one crucial drawback to using BLDC motors is the fact that they tend to perform and have great durability if the condition monitoring and fault diagnosis systems when utilized top-notch. These systems are important for the identification of abnormalities and possible defects that if not attended to can lead to major failures and long periods of non-productive time. The ability to track the state of BLDC motors in real time enables one to have preventive measures that cut the chances of the motor breaking down and consequently the costs attached to this eventuality. Condition monitoring involves continuous assessment of motor attributes such as; vibration, temperature, and electrical patterns in a bid to detect changes in healthy motor status. Whereas the existing literature on the level of faults goes beyond it by identifying the specific nature and location of the faults. Altogether, the procedures composed play the basic role of a predictive maintenance program and check BLDC motors’ performance and reliability throughout their usage. Given the importance of BLDC motors in EVs, improvements in the reliability of condition monitoring and fault diagnosis are unpreventable for the enhancement and sustainability of electric mobility.

关键词： Fault diagnosis Temperature measurement Condition monitoring Temperature sensors Vibrations machine learning Motors Electric vehicles Maintenance Monitoring

Uncertainty quantification for wide-bin unfolding: one-at-a-time strict bounds and prior-optimized confidence intervals

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Stanley, Michael Patil, Pratik Kuusela, Mikael Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics and Data Science NSF AI Planning Institute for Data-Driven Discovery in Physics Carnegie Mellon University PittsburghPA15213 United States

Unfolding is an ill-posed inverse problem in particle physics aiming to infer a true particle-level spectrum from smeared detector-level data. For computational and practical reasons, these spaces are typically discretized using histograms, and the smearing is modeled through a response matrix corresponding to a discretized smearing kernel of the particle detector. This response matrix depends on the unknown shape of the true spectrum, leading to a fundamental systematic uncertainty in the unfolding problem. To handle the ill-posed nature of the problem, common approaches regularize the problem either directly via methods such as Tikhonov regularization, or implicitly by using wide-bins in the true space that match the resolution of the detector. Unfortunately, both of these methods lead to a non-trivial bias in the unfolded estimator, thereby hampering frequentist coverage guarantees for confidence intervals constructed from these methods. We propose two new approaches to addressing the bias in the wide-bin setting through methods called One-at-a-time Strict Bounds (OSB) and Prior-Optimized (PO) intervals. The OSB intervals are a bin-wise modification of an existing guaranteed-coverage procedure, while the PO intervals are based on a decision-theoretic view of the problem. Importantly, both approaches provide well-calibrated frequentist confidence intervals even in constrained and rank-deficient settings. These methods are built upon a more general answer to the wide-bin bias problem, involving unfolding with fine bins first, followed by constructing confidence intervals for linear functionals of the fine-bin counts. We test and compare these methods to other available methodologies in a wide-bin deconvolution example and a realistic particle physics simulation of unfolding a steeply falling particle *** Codes 15A29, 62F30, 62C05, 90C90. © 2021, CC BY.

关键词： Convex optimization

Precise Asymptotics of Bagging Regularized M-estimators

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Koriyama, Takuya Patil, Pratik Du, Jin-Hong Tan, Kai Bellec, Pierre C. Booth School of Business The University of Chicago ChicagoIL60637 United States Department of Statistics University of California BerkeleyCA94720 United States Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics Rutgers University New BrunswickNJ08854 United States

We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent estimator for the risk. Specifically, we consider a heterogeneous collection of M ≥ 1 regularized M-estimators, each trained with (possibly different) subsample sizes, convex differentiable losses, and convex regularizers. We operate under the proportional asymptotics regime, where the sample size n, feature size p, and subsample sizes km for m ∈ [M] all diverge with fixed limiting ratios n/p and km/n. Key to our analysis is a new result on the joint asymptotic behavior of correlations between the estimator and residual errors on overlapping subsamples, governed through a (provably) contractible nonlinear system of equations. Of independent interest, we also establish convergence of trace functionals related to degrees of freedom in the non-ensemble setting (with M = 1) along the way, extending previously known cases for square loss and ridge, lasso regularizers. When specialized to homogeneous ensembles trained with a common loss, regularizer, and subsample size, the risk characterization sheds some light on the implicit regularization effect due to the ensemble and subsample sizes (M, k). For any ensemble size M, optimally tuning subsample size yields sample-wise monotonic risk. For the full-ensemble estimator (when M → ∞), the optimal subsample size k* tends to be in the overparameterized regime (k* ≤ min{n, p}), when explicit regularization is vanishing. Finally, joint optimization of subsample size, ensemble size, and regularization can significantly outperform regularizer optimization alone on the full data (without any subagging). Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear equations

A Review on Soil Moisture Monitoring Methods using Satellite Images

学校读者我要写书评

暂无评论

A Review on Soil Moisture Monitoring Methods using Satellite...

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Prateek Verma Aahash Kamble Aditya Barhate Abhay Tale Amit Gudadhe Department of Artificial Intelligence and Machine Learning Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Wardha Maharashtra India Department of Basic Sciences and Humanities Faculty of Engineering & Technology Datta Meghe Institute of Higher Education & Research Sawangi (Meghe) Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

Soil moisture is an important parameter in the hydrological cycle and an important component for agricultural production and prediction. The regular monitoring of soil moisture plays a big role in the prediction and management of crops and droughts in a region. Climate change has led to irregular patterns in rainfall and extreme weather conditions worldwide. This has led to the farmers taking extreme steps. The traditional method is the best method of measuring soil moisture, but it requires a lot of time and is labor-intensive. Therefore, satellite remote sensing provides an alternative approach to measuring soil moisture covering a large area within less time. The application of satellite remote sensing provides comparative results to traditional methods. This study provides a discussion on spectral indices obtained from satellite data for measuring soil moisture. The current study also provides insights about the applications, challenges, and advantages of using satellite remote sensing for monitoring of soil moisture using remote sensing datasets. The study may be helpful to farmers and government agencies for planning and management of crops and water preservation over the drought prone regions of India.

关键词： Soil measurements Moisture measurement Soil moisture Droughts Crops Satellite images Monitoring Remote sensing Farming Vegetation mapping Indexes Climate change Normalized difference vegetation index

Semi-Supervised Siamese Network for Identifying Bad data in Medical Imaging datasets

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Belton, Niamh Lawlor, Aonghus Curran, Kathleen M. Science Foundation Ireland Centre for Research Training in Machine Learning School of Medicine School of Computer Science University College Dublin Insight Centre for Data Analytics University College Dublin Dublin Ireland

Noisy data present in medical imaging datasets can often aid the development of robust models that are equipped to handle real-world data. However, if the bad data contains insufficient anatomical information, it can have a severe negative effect on the model’s performance. We propose a novel methodology using a semi-supervised Siamese network to identify bad data. This method requires only a small pool of ‘reference’ medical images to be reviewed by a non-expert human to ensure the major anatomical structures are present in the Field of View. The model trains on this reference set and identifies bad data by using the Siamese network to compute the distance between the reference set and all other medical images in the dataset. This methodology achieves an Area Under the Curve (AUC) of 0.989 for identifying bad data. Code will be available at https://***/JYFuV. © 2021, CC BY.

关键词： Medical imaging

Parameter estimation for cellular automata

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kazarnikov, Alexey Ray, Nadja Haario, Heikki Lappalainen, Joona Rupp, Andreas Heidelberg University Mathematikon Im Neuenheimer Feld 205 Heidelberg69120 Germany Mathematical Institute for Machine Learning and Data Science Catholic University of Eichstätt-Ingolstadt Hohe-Schul-Str. 5 Ingolstadt85049 Germany School of Engineering Science Lappeenranta–Lahti University of Technology P.O. Box 20 Lappeenranta53851 Finland Department of Mathematics Faculty of Mathematics and Computer Science Saarland University SaarbrückenDE-66123 Germany

Self-organizing complex systems can be modeled using cellular automaton models. However, the parametrization of these models is crucial and significantly determines the resulting structural pattern. In this research, we introduce and successfully apply a sound statistical method to estimate these parameters. The decisive difference to earlier applications of such approaches is that, in our case, both the CA rules and the resulting patterns are discrete. The method is based on constructing Gaussian likelihoods using characteristics of the structures, such as the mean particle size. We show that our approach is robust for the method parameters, domain size of patterns, or CA iterations. Copyright © 2023, The Authors. All rights reserved.

关键词： Statistical methods

COMPUTER AUDITION: FROM TASK-SPECIFIC machine learning TO FOUNDATION MODELS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Triantafyllopoulos, Andreas Tsangko, Iosif Gebhard, Alexander Mesaros, Annamaria Virtanen, Tuomas Schuller, Björn W. CHI – Chair of Health Informatics Technical University of Munich MRI Munich Germany Audio Research Group Tampere University Tampere Finland EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Augsburg Germany GLAM – Group on Language Audio & Music Imperial College London United Kingdom MCML – Munich Center for Machine Learning Munich Germany MDSI – Munich Data Science Institute Munich Germany

Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition – the use of machines to understand sounds. They feature several advantages over traditional pipelines: among others, the ability to consolidate multiple tasks in a single model, the option to leverage knowledge from other modalities, and the readily-available interaction with human users. Naturally, these promises have created substantial excitement in the audio community, and have led to a wave of early attempts to build new, general-purpose foundation models for audio. In the present contribution, we give an overview of computational audio analysis as it transitions from traditional pipelines towards auditory foundation models. Our work highlights the key operating principles that underpin those models, and showcases how they can accommodate multiple tasks that the audio community previously tackled separately. Copyright © 2024, The Authors. All rights reserved.

关键词： Pipelines