Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops

1 code implementation • 19 Nov 2020 • Florian Stelzer, André Röhm, Raul Vicente, Ingo Fischer, Serhiy Yanchuk

We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops.

Performance boost of time-delay reservoir computing by non-resonant clock cycle

no code implementations • 7 May 2019 • Florian Stelzer, André Röhm, Kathy Lüdge, Serhiy Yanchuk

Here we show that the case of equal or resonant time-delay and clock cycle could be actively detrimental and leads to an increase of the approximation error of the reservoir.

Emulating complex networks with a single delay differential equation

no code implementations • 22 Dec 2020 • Florian Stelzer, Serhiy Yanchuck

A single dynamical system with time-delayed feedback can emulate networks.

Dynamical Systems

Infinite-dimensional Folded-in-time Deep Neural Networks

no code implementations • 8 Jan 2021 • Florian Stelzer, Serhiy Yanchuk

The method recently introduced in arXiv:2011. 10115 realizes a deep neural network with just a single nonlinear element and delayed feedback.