EconPapers    
Economics at your fingertips  
 

Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

Florian Stelzer, André Röhm, Raul Vicente, Ingo Fischer and Serhiy Yanchuk ()
Additional contact information
Florian Stelzer: Technische Universität Berlin
André Röhm: IFISC (UIB-CSIC), Campus Universitat de les Illes Baleares
Raul Vicente: University of Tartu
Ingo Fischer: IFISC (UIB-CSIC), Campus Universitat de les Illes Baleares
Serhiy Yanchuk: Technische Universität Berlin

Nature Communications, 2021, vol. 12, issue 1, 1-10

Abstract: Abstract Deep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops. This single-neuron deep neural network comprises only a single nonlinearity and appropriately adjusted modulations of the feedback signals. The network states emerge in time as a temporal unfolding of the neuron’s dynamics. By adjusting the feedback-modulation within the loops, we adapt the network’s connection weights. These connection weights are determined via a back-propagation algorithm, where both the delay-induced and local network connections must be taken into account. Our approach can fully represent standard Deep Neural Networks (DNN), encompasses sparse DNNs, and extends the DNN concept toward dynamical systems implementations. The new method, which we call Folded-in-time DNN (Fit-DNN), exhibits promising performance in a set of benchmark tasks.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-25427-4 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-25427-4

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-25427-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().

 
Page updated 2025-03-19
Handle: RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-25427-4