Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-11756
For citation please use:
Main Title: Limitations of the recall capabilities in delay-based reservoir computing systems
Author(s): Köster, Felix
Ehlert, Dominik
Lüdge, Kathy
Type: Article
URI: https://depositonce.tu-berlin.de/handle/11303/12961
http://dx.doi.org/10.14279/depositonce-11756
License: https://creativecommons.org/licenses/by/4.0/
Abstract: We analyse the memory capacity of a delay-based reservoir computer with a Hopf normal form as nonlinearity and numerically compute the linear as well as the higher order recall capabilities. A possible physical realization could be a laser with external cavity, for which the information is fed via electrical injection. A task-independent quantification of the computational capability of the reservoir system is done via a complete orthonormal set of basis functions. Our results suggest that even for constant readout dimension the total memory capacity is dependent on the ratio between the information input period, also called the clock cycle, and the time delay in the system. Optimal performance is found for a time delay about 1.6 times the clock cycle.
Subject(s): lasers
nonlinear dynamics
reservoir computing
computing systems
memory capacity
Issue Date: 2-Oct-2020
Date Available: 8-Apr-2021
Language Code: en
DDC Class: 004 Datenverarbeitung; Informatik
Sponsor/Funder: TU Berlin, Open-Access-Mittel – 2020
DFG, 163436311, SFB 910: Kontrolle selbstorganisierender nichtlinearer Systeme: Theoretische Methoden und Anwendungskonzepte
Journal Title: Cognitive Computation
Publisher: SpringerNature
Publisher DOI: 10.1007/s12559-020-09733-5
EISSN: 1866-9964
ISSN: 1866-9956
TU Affiliation(s): Fak. 2 Mathematik und Naturwissenschaften » Inst. Theoretische Physik » AG Nichtlineare Laserdynamik
Appears in Collections:Technische Universität Berlin » Publications

Files in This Item:

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons