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 2012.12222math.DS
收藏

Emulating complex networks with a single delay differential equation

Florian Stelzer, Serhiy Yanchuk

英文摘要:

A single dynamical system with time-delayed feedback can emulate networks. This property of delay systems made them extremely useful tools for Machine Learning applications. Here we describe several possible setups, which allow emulating multilayer (deep) feed-forward networks as well as recurrent networks of coupled discrete maps with arbitrary adjacency matrix by a single system with delayed feedback. While the network's size can be arbitrary, the generating delay system can have a low number of variables, including a scalar case.

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。

↑