Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Xue, Yexiang"'
Discovering Ordinary Differential Equations (ODEs) from trajectory data is a crucial task in AI-driven scientific discovery. Recent methods for symbolic discovery of ODEs primarily rely on fixed training datasets collected a-priori, often leading to
Externí odkaz:
http://arxiv.org/abs/2409.01416
In reinforcement learning, Reverse Experience Replay (RER) is a recently proposed algorithm that attains better sample complexity than the classic experience replay method. RER requires the learning algorithm to update the parameters through consecut
Externí odkaz:
http://arxiv.org/abs/2408.16999
Vertical Symbolic Regression (VSR) recently has been proposed to expedite the discovery of symbolic equations with many independent variables from experimental data. VSR reduces the search spaces following the vertical discovery path by building from
Externí odkaz:
http://arxiv.org/abs/2402.00254
Automating scientific discovery has been a grand goal of Artificial Intelligence (AI) and will bring tremendous societal impact. Learning symbolic expressions from experimental data is a vital step in AI-driven scientific discovery. Despite exciting
Externí odkaz:
http://arxiv.org/abs/2312.11955
Autor:
Jacobson, Maxwell Joseph, Xue, Yexiang
Meta Reinforcement Learning (Meta RL) trains agents that adapt to fast-changing environments and tasks. Current strategies often lose adaption efficiency due to the passive nature of model exploration, causing delayed understanding of new transition
Externí odkaz:
http://arxiv.org/abs/2311.03701
Autor:
Jacobson, Maxwell Joseph, Xue, Yexiang
Design generation requires tight integration of neural and symbolic reasoning, as good design must meet explicit user needs and honor implicit rules for aesthetics, utility, and convenience. Current automated design tools driven by neural networks pr
Externí odkaz:
http://arxiv.org/abs/2310.09383
Satisfiability Modulo Counting (SMC) encompasses problems that require both symbolic decision-making and statistical reasoning. Its general formulation captures many real-world problems at the intersection of symbolic and statistical Artificial Intel
Externí odkaz:
http://arxiv.org/abs/2309.08883
The availability of tera-byte scale experiment data calls for AI driven approaches which automatically discover scientific models from data. Nonetheless, significant challenges present in AI-driven scientific discovery: (i) The annotation of large sc
Externí odkaz:
http://arxiv.org/abs/2311.12801
Autor:
Nasim, Md, Xue, Yexiang
Accelerating the learning of Partial Differential Equations (PDEs) from experimental data will speed up the pace of scientific discovery. Previous randomized algorithms exploit sparsity in PDE updates for acceleration. However such methods are applic
Externí odkaz:
http://arxiv.org/abs/2309.07344
Autor:
Jiang, Nan, Xue, Yexiang
Symbolic regression, as one of the most crucial tasks in AI for science, discovers governing equations from experimental data. Popular approaches based on genetic programming, Monte Carlo tree search, or deep reinforcement learning learn symbolic reg
Externí odkaz:
http://arxiv.org/abs/2309.07934