428 Hits in 3.8 sec

Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization

Wengang Zhang, Chongzhi Wu, Haiyi Zhong, Yongqin Li, Lin Wang
2020 Geoscience Frontiers  
To reduce the dependence on the rule of thumb and inefficient 31 brute-force search, the Bayesian optimization method is applied to determine the 32 appropriate model hyper-parameters of both XGBoost and  ...  Based on the soil data sets from TC304 database, a general approach 27 is developed to predict the USS of soft clays using the two machine learning methods 28 above, where five feature variables including  ...  It has been widely used for machine learning hyper-parameter tuning 250 recently.  ... 
doi:10.1016/j.gsf.2020.03.007 fatcat:bplpksbcozb4ldmcqx7bs6g4ea

Automated Machine Learning on Big Data using Stochastic Algorithm Tuning [article]

Thomas Nickson, Michael A Osborne, Steven Reece, Stephen J Roberts
2014 arXiv   pre-print
We introduce a means of automating machine learning (ML) for big data tasks, by performing scalable stochastic Bayesian optimisation of ML algorithm parameters and hyper-parameters.  ...  train algorithms for big data.  ...  “Algorithms for hyper-parameter optimization”.  ... 
arXiv:1407.7969v1 fatcat:nf723w7cfbbwffpimt2jvv5hku

On Hyper-parameter Tuning for Stochastic Optimization Algorithms [article]

Haotian Zhang, Jianyong Sun, Zongben Xu
2020 arXiv   pre-print
This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning.  ...  The proposed framework can be used as a standard tool for hyper-parameter tuning in stochastic algorithms.  ...  We use function set of CEC 2017 for optimization by DE and use our method to find optimal hyper-parameters. B.  ... 
arXiv:2003.02038v2 fatcat:ogioxwsojrdnrjzz2g5tyucveu

An Introduction to Neural Architecture Search for Convolutional Networks [article]

George Kyriakides, Konstantinos Margaritis
2020 arXiv   pre-print
Neural Architecture Search (NAS) is a research field concerned with utilizing optimization algorithms to design optimal neural network architectures.  ...  There are many approaches concerning the architectural search spaces, optimization algorithms, as well as candidate architecture evaluation methods.  ...  use tabular or surrogate benchmarks for in-depth evaluations.  ... 
arXiv:2005.11074v1 fatcat:dlbggh7f5vfgvirjklonhudx24

apsis - Framework for Automated Optimization of Machine Learning Hyper Parameters [article]

Frederik Diehl, Andreas Jauch
2015 arXiv   pre-print
It is implemented in Python and its architecture features adaptability to any desired machine learning code. It can easily be used with common Python ML frameworks such as scikit-learn.  ...  The apsis toolkit presented in this paper provides a flexible framework for hyperparameter optimization and includes both random search and a bayesian optimizer.  ...  Introduction Machine learning and the algorithms used for it have become more and more complex in the past years.  ... 
arXiv:1503.02946v2 fatcat:ua7rjwaknbcnjjqwk6ynzn2eve

Using Machine Learning to Predict the Fuel Peak Cladding Temperature for a Large Break Loss of Coolant Accident

Wazif Sallehhudin, Aya Diab
2021 Frontiers in Energy Research  
In this paper the use of machine learning (ML) is explored as an efficient tool for uncertainty quantification.  ...  As a bounding accident scenario analysis of the LBLOCA case paves the way to using machine learning as a decision making tool for design extension conditions as well as severe accidents.  ...  Any of these tools may be used to develop a machine learning algorithm. Each algorithm is based on its unique strategy in making predictions.  ... 
doi:10.3389/fenrg.2021.755638 fatcat:3xxipsxix5gpdm66rdmtkt3pni

Adaptive Model Predictive Control by Learning Classifiers [article]

Rel Guzman, Rafael Oliveira, Fabio Ramos
2022 arXiv   pre-print
Despite the successes, it is still unclear how to best adjust control parameters to the current task in the presence of model parameter uncertainty and heteroscedastic noise.  ...  We leverage recent results showing that BO can be reformulated via density ratio estimation, which can be efficiently approximated by simply learning a classifier.  ...  For costly system evaluations, we use surrogate-based optimization.  ... 
arXiv:2203.06783v2 fatcat:iwatvipiavcedlrihad2kchrhq

Surrogate modeling approximation using a mixture of experts based on EM joint estimation

Dimitri Bettebghor, Nathalie Bartoli, Stéphane Grihon, Joseph Morlier, Manuel Samuelides
2010 Structural And Multidisciplinary Optimization  
Lastly, the local experts are combined using the Gaussian mixture model parameters found by the EM algorithm to obtain a global model.  ...  It strongly relies on the Expectation−Maximization (EM) algorithm for Gaussian mixture models (GMM).  ...  Shahdin, from ISAE-SupAéro for their careful reading of the manuscript.  ... 
doi:10.1007/s00158-010-0554-2 fatcat:7jcj6cfdvjdvtbmx5qd4kfef64

Multi-objective parameter optimization of common land model using adaptive surrogate modeling

W. Gong, Q. Duan, J. Li, C. Wang, Z. Di, Y. Dai, A. Ye, C. Miao
2015 Hydrology and Earth System Sciences  
, (2) using surrogate models to emulate the responses of dynamic models to the variation of adjustable parameters, (3) using an adaptive strategy to improve the efficiency of surrogate modeling-based optimization  ...  ; (4) using a weighting function to transfer multi-objective optimization to single-objective optimization.  ...  A4 Support vector machine A support vector machine is an appealing machine learning method for classification and regression problems depending on the statistical learning theory (Vapnik, 1998 (Vapnik  ... 
doi:10.5194/hess-19-2409-2015 fatcat:gietgda7wzcpvlfnkrbcd3ojau

An evaluation of adaptive surrogate modeling based optimization with two benchmark problems

Chen Wang, Qingyun Duan, Wei Gong, Aizhong Ye, Zhenhua Di, Chiyuan Miao
2014 Environmental Modelling & Software  
uses cheap "surrogates" to represent the response surface of simulation models.  ...  However, ASMO can provide only approximate optimal solutions, whose precision is limited by surrogate modeling methods and problem-specific features; and 3) The identifiability of model parameters is correlated  ...  This method uses data to establish a surrogate model directly. Then it runs global optimization algorithm on the surrogate model.  ... 
doi:10.1016/j.envsoft.2014.05.026 fatcat:khipubfgvjdvrc5zf3lkxpkkli

2020 Index IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 4

2020 IEEE Transactions on Emerging Topics in Computational Intelligence  
., +, TETCI June 2020 276-286 Hyper-Parameter Optimization Using MARS Surrogate for Machine-Learning Algorithms.  ...  ., +, TETCI June 2020 369-384 Hyper-Parameter Optimization Using MARS Surrogate for Machine-Learn- ing Algorithms.  ... 
doi:10.1109/tetci.2020.3042423 fatcat:qj6bpqfey5gpjhqe7zvgg644l4

Hyper-Heuristic Coevolution of Machine Assignment and Job Sequencing Rules for Multi-Objective Dynamic Flexible Job Shop Scheduling

Yong Zhou, Jian-Jun Yang, Lian-Yu Zheng
2019 IEEE Access  
Three types of hyper-heuristic methods were proposed in this paper for coevolution of the machine assignment rules and job sequencing rules to solve the multi-objective dynamic flexible job shop scheduling  ...  The motivation of this paper is to generate effective scheduling policies (SPs) through off-line learning and to implement the evolved SPs online for fast application.  ...  A hyper-heuristic algorithm strives to find near-optimal heuristics for the problem addressed in the search space of heuristics rather than in the search space of solutions [34] .  ... 
doi:10.1109/access.2018.2883802 fatcat:hnledybojvbzpdlhndgmn6paom

A differential evolution-based regression framework for forecasting Bitcoin price

R K Jana, Indranil Ghosh, Debojyoti Das
2021 Annals of Operations Research  
Finally, we perform the numerical experimentation based on-(1) the daily closing prices of Bitcoin for January 10, 2013, to February 23, 2019, and (2) randomly generated surrogate time series through Monte  ...  Differential evolution, a metaheuristic optimization technique, helps to achieve these goals.  ...  Acknowledgements The authors thank the anonymous reviewers and the Main Guest Editor for their constructive suggestions for improving the paper.  ... 
doi:10.1007/s10479-021-04000-8 pmid:33758456 pmcid:PMC7970816 fatcat:ivcxp2k3lbha7mjwecoka35cm4

Selecting Machine Learning Algorithms Using Regression Models

Tri Doan, Jugal Kalita
2015 2015 IEEE International Conference on Data Mining Workshop (ICDMW)  
We take into account prior machine learning experience to construct metaknowledge for supervised learning.  ...  The idea is to use summary knowledge about datasets along with past performance of algorithms on these datasets to build this meta-knowledge.  ...  Using the idea of meta-learning, we solve the problem of selecting a machine learning algorithm for a particular dataset by supervised learning.  ... 
doi:10.1109/icdmw.2015.43 dblp:conf/icdm/DoanK15 fatcat:5vrgjew2tbgzvcnqq6rpelvtma

A GUI platform for uncertainty quantification of complex dynamical models

Chen Wang, Qingyun Duan, Charles H. Tong, Zhenhua Di, Wei Gong
2016 Environmental Modelling & Software  
UQ-PyL integrates different kinds of UQ methods, including experimental design, statistical analysis, sensitivity analysis, surrogate modeling and parameter optimization.  ...  It is widely used in engineering and geophysics fields to assess and predict the likelihood of various outcomes.  ...  Once the surrogate model is constructed, a global optimization algorithm can be used to identify the optimal parameter set.  ... 
doi:10.1016/j.envsoft.2015.11.004 fatcat:jibrx4ejdjhzxousrdu2vzn574
« Previous Showing results 1 — 15 out of 428 results