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 2305.08753cs.NEcs.LG
收藏

神经振荡器是通用的

Neural Oscillators are Universal

California Institute of Technology(加州理工学院);ETH Zurich(苏黎世联邦理工学院)

Samuel Lanthaler, T. Konstantin Rusch, Siddhartha Mishra

AI总结:

本研究提出神经振荡器抽象类别并证明其通用性,能逼近任意连续因果算子,为基于振荡器的机器学习系统提供理论依据。

摘要:

耦合振荡器正越来越多地被用作机器学习(ML)架构的基础,例如在序列建模、图表示学习以及用于模拟ML设备的物理神经网络中。我们引入了一个抽象类别的神经振荡器,它涵盖了这些架构,并证明了神经振荡器是通用的,即它们可以以期望的精度逼近任何连续且因果的、在时变函数之间映射的算子。这一通用性结果为基于振荡器的ML系统的使用提供了理论依据。该证明建立在一个具有独立意义的基本结果之上,该结果表明,受迫谐波振荡器与非线性读出相结合就足以逼近底层算子。

英文摘要:

Coupled oscillators are being increasingly used as the basis of machine learning (ML) architectures, for instance in sequence modeling, graph representation learning and in physical neural networks that are used in analog ML devices. We introduce an abstract class of neural oscillators that encompasses these architectures and prove that neural oscillators are universal, i.e, they can approximate any continuous and casual operator mapping between time-varying functions, to desired accuracy. This universality result provides theoretical justification for the use of oscillator based ML systems. The proof builds on a fundamental result of independent interest, which shows that a combination of forced harmonic oscillators with a nonlinear read-out suffices to approximate the underlying operators.

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。

↑