arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.05728cs.LGeess.SP
收藏

神经元先验在动态系统建模中的有效性

On the effectiveness of neural priors in modeling dynamical systems

Amazon(亚马逊);Australian Institute of Machine Learning, University of Adelaide(阿德莱德大学澳大利亚机器学习研究所)

Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey

摘要:

动态系统建模是理解自然世界的一个组成部分。为此,神经网络由于其从大量数据中学习复杂函数的能力而成为越来越受欢迎的候选者。尽管最近取得了这一进展,但在学习此类系统时,神经网络提供的架构正则化尚未得到充分讨论,这阻碍了它们的有效使用。在本文中,我们开始在这个方向上使用坐标网络作为一个试验台的讨论。我们解释动力系统和坐标网络的信号处理镜头,并表明,简单的坐标网络与几层可以用来解决多个问题的建模动力系统,没有任何明确的正则化。

英文摘要:

Modelling dynamical systems is an integral component for understanding the natural world. To this end, neural networks are becoming an increasingly popular candidate owing to their ability to learn complex functions from large amounts of data. Despite this recent progress, there has not been an adequate discussion on the architectural regularization that neural networks offer when learning such systems, hindering their efficient usage. In this paper, we initiate a discussion in this direction using coordinate networks as a test bed. We interpret dynamical systems and coordinate networks from a signal processing lens, and show that simple coordinate networks with few layers can be used to solve multiple problems in modelling dynamical systems, without any explicit regularizers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑