We present a multi-objective Bayesian active learning strategy,which greatly accelerates the discovery of super high-strength and high-ductility lead-free solder alloys.The active learning strategy demonstrates that a...We present a multi-objective Bayesian active learning strategy,which greatly accelerates the discovery of super high-strength and high-ductility lead-free solder alloys.The active learning strategy demonstrates that a machine learning model will have high generalizability if experimental data uncertainty is included,which greatly improves the model prediction or the material design accuracy.The feature-point-start forward method in multi-objective optimization adopts two Gaussian process regression(GPR)models,one for strength and one for elongation,and their outputs build up the acquisition-function-modified objective space of strength and elongation.Then,Bayesian sampling is applied to design the next experiments by balancing exploitation and exploration.Seven multi-objective active learning iterations discovered two novel super high-strength and high-ductility lead-free solder alloys.After that,various material characterizations were conducted on the two novel solder alloys,and the results exhibited their high performances in melting properties,wettability,electrical conductivity,and shear strength of the solder joint and explored the mechanism of high strength and high ductility of the alloys.The present work systematically analyzes the important role of experimental uncertainty in machine learning,especially in the global optimization for material design,which demands high generalizability of predictions.展开更多
Since requirement dependency extraction is a cognitively challenging and error-prone task,this paper proposes an automatic requirement dependency extraction method based on integrated active learning strategies.In thi...Since requirement dependency extraction is a cognitively challenging and error-prone task,this paper proposes an automatic requirement dependency extraction method based on integrated active learning strategies.In this paper,the coefficient of variation method was used to determine the corresponding weight of the impact factors from three different angles:uncertainty probability,text similarity difference degree and active learning variant prediction divergence degree.By combining the three factors with the proposed calculation formula to measure the information value of dependency pairs,the top K dependency pairs with the highest comprehensive evaluation value are selected as the optimal samples.As the optimal samples are continuously added into the initial training set,the performance of the active learning model using different dependency features for requirement dependency extraction is rapidly improved.Therefore,compared with other active learning strategies,a higher evaluation measure of requirement dependency extraction can be achieved by using the same number of samples.Finally,the proposed method using the PV-DM dependency feature improves the weight-F1 by 2.71%,the weight-recall by 2.45%,and the weight-precision by 2.64%in comparison with other strategies,saving approximately 46%of the labelled data compared with the machine learning approach.展开更多
Starting from presenting and analyzing some information gap activities during the previous teaching experience, this article has inferred the major roles of information gap activities. Some strategies to implement the...Starting from presenting and analyzing some information gap activities during the previous teaching experience, this article has inferred the major roles of information gap activities. Some strategies to implement the information gap activities are also recommended together with the functions of the instructors via these activities. What information gap activities can teach us in TESOL （teaching English for speakers of other languages） is that information gap activities contribute to setting up a climate of a mutual autonomous learning style both for the learners and the instructors, and these activities activate a diversity in the learning atmosphere.展开更多
Emerging machine learning interatomic potentials(MLIPs)offer a promising solution for large-scale accurate material simulations,but stringent tests related to the description of vibrational dynamics in molecular cryst...Emerging machine learning interatomic potentials(MLIPs)offer a promising solution for large-scale accurate material simulations,but stringent tests related to the description of vibrational dynamics in molecular crystals remain scarce.Here,we develop a general MLIP by leveraging the graph neural network-based MACE architecture and active-learning strategies to accurately capture vibrational dynamics across a range of polyacene-based molecular crystals,namely naphthalene,anthracene,tetracene and pentacene.Through careful error propagation,we show that these potentials are accurate and enable the study of anharmonic vibrational features,vibrational lifetimes,and vibrational coupling.In particular,we investigate large-scale host-vip systems based on these molecular crystals,showing the capacity of molecular-dynamics-based techniques to explain and quantify vibrational coupling between host and vip nuclear motion.Our results establish a framework for understanding vibrational signatures in large-scale complex molecular systems and thus represent an important step for engineering vibrational interactions in molecular environments.展开更多
We present new parameterizations of the ChIMES physics informed machine-learned interatomic model for simulating carbon under conditions ranging from 300 K and 0 GPa to 10,000 K and 100 GPa,along with a new multi-fide...We present new parameterizations of the ChIMES physics informed machine-learned interatomic model for simulating carbon under conditions ranging from 300 K and 0 GPa to 10,000 K and 100 GPa,along with a new multi-fidelity active learning strategy.The resulting models show significant improvement in accuracy and temperature/pressure transferability relative to the original ChIMES carbon model developed in 2017 and can serve as a foundation for future transfer-learned ChIMES parameter sets.Applications to carbon melting point prediction,shockwave-driven conversion of graphite to diamond,and thermal conversion of nanodiamond to graphitic nanoonion are provided.Ultimately,we find the new models to be robust,accurate,and well-suited for modeling evolution in carbon systems under extreme conditions.展开更多
基金sponsored by the Shanghai Pujiang Program(Grant no.20PJ1403700)the Guangzhou-HKUST(GZ)Joint Funding Program(nos.2023A03J0003 and 2023A03J0103)the Opening Project Fund of Materials Service Safety Assessment Facilities(MSAF-2024-107).
文摘We present a multi-objective Bayesian active learning strategy,which greatly accelerates the discovery of super high-strength and high-ductility lead-free solder alloys.The active learning strategy demonstrates that a machine learning model will have high generalizability if experimental data uncertainty is included,which greatly improves the model prediction or the material design accuracy.The feature-point-start forward method in multi-objective optimization adopts two Gaussian process regression(GPR)models,one for strength and one for elongation,and their outputs build up the acquisition-function-modified objective space of strength and elongation.Then,Bayesian sampling is applied to design the next experiments by balancing exploitation and exploration.Seven multi-objective active learning iterations discovered two novel super high-strength and high-ductility lead-free solder alloys.After that,various material characterizations were conducted on the two novel solder alloys,and the results exhibited their high performances in melting properties,wettability,electrical conductivity,and shear strength of the solder joint and explored the mechanism of high strength and high ductility of the alloys.The present work systematically analyzes the important role of experimental uncertainty in machine learning,especially in the global optimization for material design,which demands high generalizability of predictions.
基金supported by the Scientific Research Funding Project of Education Department of Liaoning Province 2021,China(No.LJKZ0434).
文摘Since requirement dependency extraction is a cognitively challenging and error-prone task,this paper proposes an automatic requirement dependency extraction method based on integrated active learning strategies.In this paper,the coefficient of variation method was used to determine the corresponding weight of the impact factors from three different angles:uncertainty probability,text similarity difference degree and active learning variant prediction divergence degree.By combining the three factors with the proposed calculation formula to measure the information value of dependency pairs,the top K dependency pairs with the highest comprehensive evaluation value are selected as the optimal samples.As the optimal samples are continuously added into the initial training set,the performance of the active learning model using different dependency features for requirement dependency extraction is rapidly improved.Therefore,compared with other active learning strategies,a higher evaluation measure of requirement dependency extraction can be achieved by using the same number of samples.Finally,the proposed method using the PV-DM dependency feature improves the weight-F1 by 2.71%,the weight-recall by 2.45%,and the weight-precision by 2.64%in comparison with other strategies,saving approximately 46%of the labelled data compared with the machine learning approach.
文摘Starting from presenting and analyzing some information gap activities during the previous teaching experience, this article has inferred the major roles of information gap activities. Some strategies to implement the information gap activities are also recommended together with the functions of the instructors via these activities. What information gap activities can teach us in TESOL （teaching English for speakers of other languages） is that information gap activities contribute to setting up a climate of a mutual autonomous learning style both for the learners and the instructors, and these activities activate a diversity in the learning atmosphere.
基金support from the Cluster of Excellence“CUI:Advanced Imaging of Matter”—EXC 2056—project ID 390715994BiGmax,the Max Planck Society Research Network on Big-Data-Driven Materials-Science and the Max Planck-New York City Center for Non-Equilibrium Quantum Phenomena.The Flatiron Institute is a division of the Simons Foundation+1 种基金We also acknowledge support from the European Research Council MSCA-ITN TIMES under grant agreement 101118915S.S.and P.L.acknowledge support from the UFAST International Max Planck Research School.
文摘Emerging machine learning interatomic potentials(MLIPs)offer a promising solution for large-scale accurate material simulations,but stringent tests related to the description of vibrational dynamics in molecular crystals remain scarce.Here,we develop a general MLIP by leveraging the graph neural network-based MACE architecture and active-learning strategies to accurately capture vibrational dynamics across a range of polyacene-based molecular crystals,namely naphthalene,anthracene,tetracene and pentacene.Through careful error propagation,we show that these potentials are accurate and enable the study of anharmonic vibrational features,vibrational lifetimes,and vibrational coupling.In particular,we investigate large-scale host-vip systems based on these molecular crystals,showing the capacity of molecular-dynamics-based techniques to explain and quantify vibrational coupling between host and vip nuclear motion.Our results establish a framework for understanding vibrational signatures in large-scale complex molecular systems and thus represent an important step for engineering vibrational interactions in molecular environments.
基金supported by LLNL LDRD 23-SI-006.LLNL-JRNL-861515.
文摘We present new parameterizations of the ChIMES physics informed machine-learned interatomic model for simulating carbon under conditions ranging from 300 K and 0 GPa to 10,000 K and 100 GPa,along with a new multi-fidelity active learning strategy.The resulting models show significant improvement in accuracy and temperature/pressure transferability relative to the original ChIMES carbon model developed in 2017 and can serve as a foundation for future transfer-learned ChIMES parameter sets.Applications to carbon melting point prediction,shockwave-driven conversion of graphite to diamond,and thermal conversion of nanodiamond to graphitic nanoonion are provided.Ultimately,we find the new models to be robust,accurate,and well-suited for modeling evolution in carbon systems under extreme conditions.
