Filters








112 Hits in 3.8 sec

A Quantum-Inspired Ensemble Method and Quantum-Inspired Forest Regressors [article]

Zeke Xie, Issei Sato
2017 arXiv   pre-print
We incorporate Quantum-Inspired Subspace Method into Random Forest and propose Quantum-Inspired Forest.  ...  We propose a Quantum-Inspired Subspace(QIS) Ensemble Method for generating feature ensembles based on feature selections.  ...  First, we propose a novel ensemble method named Quantum-Inspired Subspace and Quantum-Inspired Forest.  ... 
arXiv:1711.08117v1 fatcat:pg3mlubvdnbelohsi4uajtr3e4

Two Machine-learning Approaches for Short-term COVID-19 Hospitalization Forecasting in Slovakia

Veronika Kurilova, Martin Huba, Jozef Goga, Milos Oravec, Jarmila Pavlovicova, Nora Majtánová
2021 Conference on Theory and Practice of Information Technologies  
Our study focused on short-term COVID-19 hospitalizations forecasting using two machine learning approaches-ensemble time-series method and multilayer perceptron (MLP) feedforward network method.  ...  COVID-19 is a life-threatening novel respiratory virus-borne disease, which was discovered in December 2019 in Wuhan and subsequently spread globally.  ...  The model consists of six soft voting base regressors: three gradient boosting regressors, one random forest regressor and two decision tree regressors, each with different parameters.  ... 
dblp:conf/itat/KurilovaHGOPM21 fatcat:llrxzf4wxbgd5iwq7vxb6dnkau

Symbolic regression outperforms other models for small data sets [article]

Casper Wilstrup, Jaan Kasak
2021 arXiv   pre-print
Traditional machine learning techniques, such as random forests and gradient boosting, tend to overfit when working with data sets of only a few hundred observations.  ...  The second best algorithm was found to be a random forest, which performs best in 37 of the 240 cases.  ...  The company Abzu, which employs the authors of this article, has recently developed a symbolic regressor inspired by quantum field theory known as the QLattice [19] .  ... 
arXiv:2103.15147v3 fatcat:n6pozzlitrfmvijaefrbgxoo2m

Robust near real-time estimation of physiological parameters from megapixel multispectral images with inverse Monte Carlo and random forest regression

Sebastian J. Wirkert, Hannes Kenngott, Benjamin Mayer, Patrick Mietkowski, Martin Wagner, Peter Sauer, Neil T. Clancy, Daniel S. Elson, Lena Maier-Hein
2016 International Journal of Computer Assisted Radiology and Surgery  
Our concept is based on training random forest regressors using B Sebastian J. Wirkert reflectance spectra generated with Monte Carlo simulations.  ...  The goal of this work was to develop a method to estimate physiological parameters in an accurate and rapid manner suited for modern high-resolution laparoscopic images.  ...  reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s11548-016-1376-5 pmid:27142459 pmcid:PMC4893375 fatcat:fpoup7jamvabbbyfiir3rsbrea

A Hybrid Method Using HAVOK Analysis and Machine Learning for Predicting Chaotic Time Series

Jinhui Yang, Juan Zhao, Junqiang Song, Jianping Wu, Chengwu Zhao, Hongze Leng
2022 Entropy  
A hybrid method using Hankel Alternative View Of Koopman (HAVOK) analysis and machine learning (HAVOK-ML) is developed to predict chaotic time series.  ...  The prediction performance evaluations confirm that the proposed method has superior forecasting skills compared with existing prediction methods.  ...  Model RMSE NMSE Reference ARMA with Maximal Overlap Dis- / 5.3373 × 10 −7 [16] crete Wavelet Transform Ensembles of Recurrent Neural Net- 7.533 × 10 −3 8.29 × 10 −4 [20] work Quantum-Inspired Neural Network  ... 
doi:10.3390/e24030408 pmid:35327919 pmcid:PMC8947207 fatcat:s3r5n7t3ubbjtnbugitsd4zz6q

Accurate Prediction of Chemical Shifts for Aqueous Protein Structure for "Real World" Cases using Machine Learning [article]

Jie Li, Kochise C. Bennett, Yuchen Liu, Michael V. Martin, Teresa Head-Gordon
2019 arXiv   pre-print
, and a redesigned machine learning module based on random forest regression which utilizes more, and more carefully curated, feature extracted data.  ...  Our UCBShift predictor implements two modules: a transfer prediction module that employs both sequence and structural alignment to select reference candidates for experimental chemical shift replication  ...  Both the extra tree regressor and random forest regressor are ensembles of tree regressors that split the data using a subset of the features, and make ensemble-based predictions via a majority vote.  ... 
arXiv:1912.02735v1 fatcat:72nmwbygn5hyjdgiwd54eun5bq

Accurate Prediction of Chemical Shifts for Aqueous Protein Structure on "Real World" Data

Jerry Li, Kochise C Bennett, Yuchen Liu, Michael V Martin, Teresa Head-Gordon
2020 Chemical Science  
Here we report a new machine learning algorithm for protein chemical shift prediction that outperforms existing chemical shift calculators on realistic data that is not heavily curated, nor eliminates  ...  Acknowledgements We thank Mojtaba Haghighatlari, Brad Ganoe, Tim Stauch, Lars Urban, Shuai Liu, and Martin Head-Gordon for fruitful discussions.  ...  Both the extra tree regressor and random forest regressor are ensembles of tree regressors that split the data using a subset of the features, and make ensemble-based predictions via a majority vote.  ... 
doi:10.1039/c9sc06561j pmid:34122823 pmcid:PMC8152569 fatcat:mg2rkcugabaqtaduanhlcuhxxm

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery.  ...  In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.  ...  Along this line, many quantum mechanical methods based on DFT have been developed to model the quantum interactions of molecules for the prediction (Hohenberg and Kohn 1964; Kohn and Sham 1965) .  ... 
doi:10.1609/aaai.v33i01.33011052 fatcat:zseoxqmawnbflf33i3duogi6qm

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective [article]

Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
2019 arXiv   pre-print
., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery.  ...  In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.  ...  Along this line, many quantum mechanical methods based on DFT have been developed to model the quantum interactions of molecules for the prediction (Hohenberg and Kohn 1964; Kohn and Sham 1965) .  ... 
arXiv:1906.11081v1 fatcat:5xtcjvez6bd2rg4tkgun33aqte

MoleculeNet: a benchmark for molecular machine learning

Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, Vijay Pande
2018 Chemical Science  
A large scale benchmark for molecular machine learning consisting of multiple public datasets, metrics, featurizations and learning algorithms.  ...  Acknowledgements We would like to thank the Stanford Computing Resources for providing us with access to the Sherlock and Xstream GPU nodes. Thanks to Steven Kearnes  ...  Random forests (RF) are ensemble prediction methods. 72 A random forest consists of many individual decision trees, each of which is trained on a subsampled version of the original dataset.  ... 
doi:10.1039/c7sc02664a pmid:29629118 pmcid:PMC5868307 fatcat:5ywwlxwx35hofo45awl4bdmjqq

Adaptive Particle Swarm Optimization Algorithm Ensemble Model Applied to Classification of Unbalanced Data

Dawei Zheng, Chao Qin, Peipei Liu, Pengwei Wang
2021 Scientific Programming  
Unbalanced data classification is a major challenge in the field of data mining. Random forest, as an ensemble learning method, is usually used to solve the problem of unbalanced data classification.  ...  This paper proposes a random forest-based adaptive particle swarm optimization on data classification, and an adaptive particle swarm used to optimize the hyperparameters in the random forest to ensure  ...  classifier has better learning ability than a single classifier. e Random Forest (RF) algorithm is a bagging ensemble learning algorithm based on the random subspace method proposed by Bierman et al  ... 
doi:10.1155/2021/7589756 fatcat:v3blvvhlczcirod3g3okcyny7u

Ab initio machine learning in chemical compound space [article]

Bing Huang, O. Anatole von Lilienfeld
2021 arXiv   pre-print
inspired by quantum mechanics.  ...  We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures  ...  If regressor, metric and representation M are independent of the label, i.e. the quantum property, there is a strict analogy to quantum mechanics in the sense of the Hamiltonian (or the wavefunction) of  ... 
arXiv:2012.07502v4 fatcat:2sfiyd5uwzdblafxjv4vmh3ule

Ab Initio Machine Learning in Chemical Compound Space

Bing Huang, O. Anatole von Lilienfeld
2021 Chemical Reviews  
inspired by quantum mechanics.  ...  We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures  ...  Wagner and F. A. Faber for helping with the design of Figures 1 and 2  ... 
doi:10.1021/acs.chemrev.0c01303 pmid:34387476 pmcid:PMC8391942 fatcat:k7tezwtjivhklj5rcwsm6vjhgi

MoleculeNet: A Benchmark for Molecular Machine Learning [article]

Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, Vijay Pande
2018 arXiv   pre-print
For quantum mechanical and biophysical datasets, the use of physics-aware featurizations can be more important than choice of particular learning algorithm.  ...  However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are benchmarked on different datasets making it challenging  ...  Random Forests Random forests (RF) are ensemble prediction methods. 72 A random forest consists of many individual decision trees, each of which is trained on a subsampled version of the original dataset  ... 
arXiv:1703.00564v3 fatcat:pmhnvly7qfhrxkel5a6tctowv4

Parasitic resistance as a predictor of faulty anodes in electro galvanizing: a comparison of machine learning, physical and hybrid models

Mario Lovrić, Richard Meister, Thomas Steck, Leon Fadljević, Johann Gerdenitsch, Stefan Schuster, Lukas Schiefermüller, Stefanie Lindstaedt, Roman Kern
2020 Advanced Modeling and Simulation in Engineering Sciences  
For predictive modelling, we used Random Forest, Partial Least Squares and AdaBoost Regression.  ...  The best-performing model is a hybrid version of a Random Forest which incorporates meta-variables computed from the physical model.  ...  A detailed overview of the method is presented in Refs. [35, 36] . Ensemble regressors The Random Forest algorithm, conceptualized by Breiman [37] , achieves prediction by exploiting bagging.  ... 
doi:10.1186/s40323-020-00184-z fatcat:pqhcqspcrrg3vd7f2ybjkizqoa
« Previous Showing results 1 — 15 out of 112 results