期刊
IEEE ACCESS
卷 9, 期 -, 页码 114246-114254出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3103876
关键词
Physics; Observers; Mathematical model; Convolutional neural networks; Artificial intelligence; Three-dimensional displays; Differential equations; Artificial intelligence; artificial neural network; classical physics; intuitive physics; non-inertial system
资金
- Institute for Information & Communications Technology Planning & Evaluation (IITP) - Korea government [Ministry of Science and Information and Communication Technology (MSIT)] [2019-0-01371]
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [NRF-2019M3E5D2A01066267]
- Institute for Information & Communications Technology Promotion (IITP) - Korea government [2017-0-00451]
- Ministry of Culture, Sports, and Tourism(MCST)
- Korea Creative Content Agency(KOCCA) in the Culture Technology(CT) Research & Development Program [(R2020060002) 2021]
The study found that neural network-based intuitive physics can successfully solve problems in non-inertial reference frames, which is an ability to understand and predict physical phenomena in advance. The research designed three experiments to represent different types of challenges and demonstrated that neural network methods can learn the underlying dynamics of objects from observations.
Classical mechanics offers us reliable means to predict various physical quantities, but it is difficult to derive the precise dynamic equations underlying most phenomena and obtain physical quantities in real-world situations. Intuitive physics, the ability to intuitively understand and predict physical phenomena, prevents this complication. However, its applications are confined to the inertial frame of reference. Here, we explored the potentials of neural network-based intuitive physics for solving non-inertial reference frames. We designed three experiments, each of which represents different types of real-world challenges. The task required predicting the speed of an object while the observer accelerates. We demonstrated that multilayer perceptron, invariant methods, and long-term memory networks successfully learn underlying dynamics from observations. This implies that neural network-based intuitive physics provides alternative means to predict various quantities in real-world applications that are unsolvable by classical physics methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据