Filters








114,685 Hits in 4.2 sec

Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework

Jin-Long Wu, Heng Xiao, Eric Paterson
2018 Physical Review Fluids  
Second, we propose using machine learning to predict linear and nonlinear parts of the Reynolds stress tensor separately.  ...  Recently, Wang et al. demonstrated that machine learning can be used to improve the RANS modeled Reynolds stresses by leveraging data from high fidelity simulations (Physics informed machine learning approach  ...  Data augmentation for achieving invariance in machine learning. In machine learning the lack of invariance property in the model to be learned from data can be remedied by data augmentation [6] .  ... 
doi:10.1103/physrevfluids.3.074602 fatcat:pz6epa6nlnhjlj5hnxwwofum3i

Design of a Data-Driven Multi PID Controllers using Ensemble Learning and VRFT

Takuya Kinoshita, Yuma Morota, Toru Yamamoto
2020 Journal of Robotics, Networking and Artificial Life (JRNAL)  
In this study, a design scheme of data-driven controllers using the ensemble learning and VRFT is newly proposed for linear time-varying systems.  ...  Specifically, the Virtual Reference Feedback Tuning (VRFT) has been proposed for linear time-invariant systems.  ...  Specifically, a linear time-invariant system is first divided into some linear systems by applying ensemble learning based on decision tree learning.  ... 
doi:10.2991/jrnal.k.200512.014 fatcat:tanua6rq6bgghaxout2iepkjtq

On Scaling Data-Driven Loop Invariant Inference [article]

Sahil Bhatia, Saswat Padhi, Nagarajan Natarajan, Rahul Sharma, Prateek Jain
2020 arXiv   pre-print
In this paper, we study these scalability issues and address them in our tool oasis that improves the scale of data-driven invariant inference and outperforms state-of-the-art systems on benchmarks from  ...  Although static analyses to infer invariants have been studied for over forty years, recent years have seen a flurry of data-driven invariant inference techniques which guess invariants from examples instead  ...  At the heart of the data-driven techniques is an active learning [Hanneke 2009] loop: a learner guesses a candidate invariant from data and provides the candidate to a teacher.  ... 
arXiv:1911.11728v2 fatcat:qtqbwjoln5f6fnetgf7u5gp24i

LoopInvGen: A Loop Invariant Generator based on Precondition Inference [article]

Saswat Padhi and Rahul Sharma and Todd Millstein
2019 arXiv   pre-print
We describe the LoopInvGen tool for generating loop invariants that can provably guarantee correctness of a program with respect to a given specification.  ...  In contrast to existing techniques, LoopInvGen is not restricted to a fixed set of features -- atomic predicates that are composed together to build complex loop invariants.  ...  ACKNOWLEDGMENT We thank the organizers of SyGuS-Comp for making all the solvers and benchmarks publicly available.  ... 
arXiv:1707.02029v4 fatcat:mywfv2j3x5c7vdkxpvq67cjx5e

Constitutive artificial neural networks : a general anisotropic constitutive modeling framework utilizing machine learning

Markus Hillgärtner, Kevin Linka, Kian P. Abdolazizi, Roland C. Aydin, Mikhail Itskov, Christian J. Cyron
2021 91st Annual Meeting of the International Association of Applied Mathematics and Mechanics  
In this contribution, a novel machine learning architecture for data-driven modeling of the mechanical constitutive behavior of materials, constitutive artificial neural networks (CANNs) [1], will be introduced  ...  With only a low-to-moderate amount of training data and training time, they can predict the constitutive behavior of complex nonlinear and anisotropic materials.  ...  Acknowledgements Open access funding enabled and organized by Projekt DEAL.  ... 
doi:10.18154/rwth-2021-11997 fatcat:zzro6qzsa5ewfjx63x3ebecfkm

Deep Learning Enable Diagnostics and Prognostics of Machine Health Condition

Wo Jae Lee, John W. Sutherland
2019 Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM  
The paper covers the development and application of data-driven approaches to machine health management.  ...  This paper presents an overview of the first author's research being conducted and future research plans for the rest of PhD career.  ...  The challenge of the data-driven model is it requires a huge amount of labelled data for model training and validation.  ... 
doi:10.36001/phmconf.2019.v11i1.919 fatcat:3mun4kovtbhfpnwaxcdnsdhdt4

Data-based guarantees of set invariance properties

Andrea Bisoffi, Claudio De Persis, Pietro Tesi
2020 IFAC-PapersOnLine  
For a discrete-time linear system, we use data from an open-loop experiment to design directly a linear feedback controller enforcing that a given (polyhedral) set of the state is invariant and given (  ...  The satisfaction of the above properties is guaranteed only from data, it can be assessed by solving a numericallyefficient linear program, and, under a certain rank condition, a data-based solution is  ...  Specifically, we consider linear time invariant systems in discrete time and study the problem of designing a control law based on a finite number of input-state data in such a way that the controlled  ... 
doi:10.1016/j.ifacol.2020.12.2250 fatcat:dj2e25wuvbgdvhdiqu5zw4ytcq

View-invariance learning in object recognition by pigeons depends on error-driven associative learning processes

Fabian A. Soto, Jeffrey Y.M. Siow, Edward A. Wasserman
2012 Vision Research  
A model hypothesizing that basic mechanisms of associative learning and generalization underlie object categorization in vertebrates can account for a large body of animal and human data.  ...  Here, we report two experiments which implicate error-driven associative learning in pigeons' recognition of objects across changes in viewpoint.  ...  Wasserman, and by National Eye Institute Grant EY019781 to Edward A. Wasserman.  ... 
doi:10.1016/j.visres.2012.04.004 pmid:22531015 pmcid:PMC3361566 fatcat:dwu6hwycurhlbchymx3dvibupe

Zenet

Chris Lewis
2010 Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering - ICSE '10  
Generating correct specifications for real-time event-driven software systems is difficult and time-consuming.  ...  We propose a specification generator that reads execution traces and can generate invariants with real-time constraints.  ...  We believe creating these specifications from the event streams outputted by the execution of event-driven systems will create a powerful, scalable tool that can detect and enforce correct operation of  ... 
doi:10.1145/1810295.1810377 dblp:conf/icse/Lewis10 fatcat:r2ppoa6ozfdgvauxf3yz4jze7a

Unsupervised deep learning for individualized brain functional network identification [article]

Hongming Li, Yong Fan
2020 arXiv   pre-print
Moreover, a time-invariant representation learning module is designed to learn features invariant to temporal orders of time points of rsfMRI data.  ...  Particularly, convolutional neural networks (CNNs) with an Encoder-Decoder architecture are adopted to identify individual-specific FNs from rsfMRI data by optimizing their data fitting and sparsity regularization  ...  ] module to identify FNs at individual level and a time-invariant representation learning module to learn features invariant to temporal orders of time points of rsfMRI data.  ... 
arXiv:2012.06494v1 fatcat:tm4swldr7bht3ad7w5iulqylae

Ensemble Kalman method for learning turbulence models from indirect observation data [article]

Xin-Lei Zhang, Heng Xiao, Xiaodong Luo, Guowei He
2022 arXiv   pre-print
Then, the generalizability of the learned model is evaluated on a family of separated flows over periodic hills.  ...  However, this would necessitate developing adjoint solvers of the RANS model, which requires extra effort in code development and maintenance.  ...  Finally, the authors thank the reviewers for their constructive and valuable comments, which greatly improved the quality and clarity of this paper.  ... 
arXiv:2202.05122v4 fatcat:73hwx7lr5fhpnbvqcipia2vkum

Invariant Synthesis for Incomplete Verification Engines [chapter]

Daniel Neider, Pranav Garg, P. Madhusudan, Shambwaditya Saha, Daejun Park
2018 Lecture Notes in Computer Science  
We show precisely how the verification engine can compute such non-provability information and how to build effective learning algorithms when invariants are expressed as Boolean combinations of a fixed  ...  set of predicates.  ...  Complementing them are data-driven invariant synthesis techniques based on learning, such as Daikon [13] that learn likely invariants, and Houdini [14] and ICE [17] that learn inductive invariants  ... 
doi:10.1007/978-3-319-89960-2_13 fatcat:saysfl3slnbn3mktsvtqk7mnlm

Learning Nonlinear Loop Invariants with Gated Continuous Logic Networks (Extended Version) [article]

Jianan Yao, Gabriel Ryan, Justin Wong, Suman Jana, Ronghui Gu
2020 arXiv   pre-print
However, applying data-driven inference to nonlinear loop invariants is challenging due to the large numbers of and magnitudes of high-order terms, the potential for overfitting on a small number of samples  ...  Recently, data-driven methods for loop invariant inference have shown promise, especially on linear invariants.  ...  Acknowledgements The authors are grateful to our shepherd, Aditya Kanade, and the anonymous reviewers for valuable feedbacks that improved this paper significantly.  ... 
arXiv:2003.07959v4 fatcat:j3m343yaqjbyhjwadw4swoes4u

Detecting and Localizing 3D Object Classes using Viewpoint Invariant Reference Frames

Matthew Toews, Tal Arbel
2007 2007 IEEE 11th International Conference on Computer Vision  
We present a new, iterative learning algorithm to determine an optimal viewpoint invariant reference frame from training images in a data-driven manner.  ...  We compare multi-view and viewpoint invariant representations trained and tested on the same data, where the viewpoint invariant approach results in fewer false positive detections and higher average precision  ...  In Section 3.3, we propose an iterative algorithm for learning an optimal invariant reference frame in a data-driven manner.  ... 
doi:10.1109/iccv.2007.4408832 dblp:conf/iccv/ToewsA07 fatcat:si4cwyi24bfhpjoltdr45bnuwu

Distilling Localization for Self-Supervised Representation Learning [article]

Nanxuan Zhao, Zhirong Wu, Rynson W.H. Lau, Stephen Lin
2021 arXiv   pre-print
To address this problem, we propose a data-driven approach for learning invariance to backgrounds.  ...  We study a variety of saliency estimation methods, and find that most methods lead to improvements for contrastive learning.  ...  We first revisit a recent data-driven method for learning invariance, and then describe our approach.  ... 
arXiv:2004.06638v2 fatcat:36x43zh5vvg3pbsvak7wf3nwci
« Previous Showing results 1 — 15 out of 114,685 results