Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empi...Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empirical performance,the theoretical foundations of deep multi-modal learning have yet to be fully explored.In this paper,we will undertake a comprehensive survey of recent developments in multi-modal learning theories,focusing on the fundamental properties that govern this field.Our goal is to provide a thorough collection of current theoretical tools for analyzing multi-modal learning,to clarify their implications for practitioners,and to suggest future directions for the establishment of a solid theoretical foundation for deep multi-modal learning.展开更多
Artificial intelligence (AI) is almo st everywhere due to the rapid development of modern technology and popularity of intelligent devices.While control theory and machine learning techniques as two enabling technolog...Artificial intelligence (AI) is almo st everywhere due to the rapid development of modern technology and popularity of intelligent devices.While control theory and machine learning techniques as two enabling technologies have shown enormous power in their own right,a rapprochement of them is required to handle nonlinearity,uncertainty and scalability induced by high complexity of modern systems,huge quantity of real-time data,and large scale of agent networks.Journal of Automation and Intelligence (JAI) aims to provide a platform for researchers and practitioners from both academia and industry to exchange their ideas and present new developments across multiple disciplines relevant to automation and artificial intelligence with particular attention to machine learning.展开更多
A machine learning enabled computational approach has been developed to accurately predict the equilibrium degree of inversion in spinel lattice and some magnetic properties of cobalt ferrite(CoFe_(2)O_(4))crystal.The...A machine learning enabled computational approach has been developed to accurately predict the equilibrium degree of inversion in spinel lattice and some magnetic properties of cobalt ferrite(CoFe_(2)O_(4))crystal.The computational approach is composed of construction of a database from density functional theory calculations,training of machine learning models,and atomistic simulations.Support vector regression was employed to derive the relation between system energy and atomic structures of CoFe_(2)O_(4).Using this trained machine learning model,atomistic Monte Carlo simulations predicted the equilibrium degree of inversion of CoFe_(2)O_(4)to be 0.755 at 1237 K.The strength of twenty-three types of superexchange interactions were determined using the linear regression model and further applied in magnetic Monte Carlo simulations to predict the Curie temperature of CoFe_(2)O_(4)to be 914 K.The predictions from the presented computational approach are well validated by the results from neutron diffraction measurement on CoFe_(2)O_(4).展开更多
基金Supported by Technology and Innovation Major Project of the Ministry of Science and Technology of China(2020AAA0108400, 2020AAA0108403)Tsinghua Precision Medicine Foundation(10001020109)。
文摘Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empirical performance,the theoretical foundations of deep multi-modal learning have yet to be fully explored.In this paper,we will undertake a comprehensive survey of recent developments in multi-modal learning theories,focusing on the fundamental properties that govern this field.Our goal is to provide a thorough collection of current theoretical tools for analyzing multi-modal learning,to clarify their implications for practitioners,and to suggest future directions for the establishment of a solid theoretical foundation for deep multi-modal learning.
文摘Artificial intelligence (AI) is almo st everywhere due to the rapid development of modern technology and popularity of intelligent devices.While control theory and machine learning techniques as two enabling technologies have shown enormous power in their own right,a rapprochement of them is required to handle nonlinearity,uncertainty and scalability induced by high complexity of modern systems,huge quantity of real-time data,and large scale of agent networks.Journal of Automation and Intelligence (JAI) aims to provide a platform for researchers and practitioners from both academia and industry to exchange their ideas and present new developments across multiple disciplines relevant to automation and artificial intelligence with particular attention to machine learning.
基金the supports from U.S.National Science Foundation(NSF DMR#1905572 and NSF CMMI#1760916)support from the Office of Naval Research(ONR GRANT#N000142112498)+1 种基金supported in part by the University of Pittsburgh Center for Research Computing,RRID:SCR_022735,through the computer resources provided.Specifically,this work used the H2P clustersupported by NSF award number OAC-2117681.A portion of this research used resources at the High Flux Isotope Reactor,a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory.
文摘A machine learning enabled computational approach has been developed to accurately predict the equilibrium degree of inversion in spinel lattice and some magnetic properties of cobalt ferrite(CoFe_(2)O_(4))crystal.The computational approach is composed of construction of a database from density functional theory calculations,training of machine learning models,and atomistic simulations.Support vector regression was employed to derive the relation between system energy and atomic structures of CoFe_(2)O_(4).Using this trained machine learning model,atomistic Monte Carlo simulations predicted the equilibrium degree of inversion of CoFe_(2)O_(4)to be 0.755 at 1237 K.The strength of twenty-three types of superexchange interactions were determined using the linear regression model and further applied in magnetic Monte Carlo simulations to predict the Curie temperature of CoFe_(2)O_(4)to be 914 K.The predictions from the presented computational approach are well validated by the results from neutron diffraction measurement on CoFe_(2)O_(4).
