scholarly journals Deep time-delay reservoir computing: Dynamics and memory capacity

2020 ◽  
Vol 30 (9) ◽  
pp. 093124
Author(s):  
Mirko Goldmann ◽  
Felix Köster ◽  
Kathy Lüdge ◽  
Serhiy Yanchuk
Keyword(s):  
Time Delay ◽  
Memory Capacity ◽  
Reservoir Computing ◽  
Deep Time

scholarly journals Limitations of the Recall Capabilities in Delay-Based Reservoir Computing Systems

2020 ◽  
Author(s):  
Felix Köster ◽  
Dominik Ehlert ◽  
Kathy Lüdge
Keyword(s):  
Time Delay ◽  
Clock Cycle ◽  
External Cavity ◽  
Memory Capacity ◽  
Basis Functions ◽  
Reservoir Computing ◽  
Computing Systems ◽  
Computational Capability ◽  
System Optimal ◽  
Information Input

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.

scholarly journals Reservoir computing with a single time-delay autonomous Boolean node

2015 ◽  
Vol 91 (2) ◽  
Author(s):  
Nicholas D. Haynes ◽  
Miguel C. Soriano ◽  
David P. Rosin ◽  
Ingo Fischer ◽  
Daniel J. Gauthier
Keyword(s):  
Time Delay ◽  
Reservoir Computing ◽  
Single Time

5. Time delay systems for reservoir computing

2019 ◽  
pp. 117-152
Author(s):  
Silvia Ortín ◽  
Luis Pesquera ◽  
Guy Van der Sande ◽  
Miguel C. Soriano
Keyword(s):  
Time Delay ◽  
Delay Systems ◽  
Reservoir Computing ◽  
Time Delay Systems

scholarly journals Microring resonators with external optical feedback for time delay reservoir computing

2021 ◽  
Author(s):  
Giovanni Donati ◽  
Claudio Mirasso ◽  
Mattia Mancinelli ◽  
Lorenzo Pavesi ◽  
Apostolos Argyris
Keyword(s):  
Time Delay ◽  
Optical Feedback ◽  
Microring Resonators ◽  
Reservoir Computing

scholarly journals Delayed dynamical systems: networks, chimeras and reservoir computing

2019 ◽  
Vol 377 (2153) ◽  
pp. 20180123 ◽  
Author(s):  
Joseph D. Hart ◽  
Laurent Larger ◽  
Thomas E. Murphy ◽  
Rajarshi Roy
Keyword(s):  
Time Delay ◽  
Dynamical Systems ◽  
System Dynamics ◽  
Coupled Oscillators ◽  
Time Delays ◽  
Delay Systems ◽  
Multiple Time ◽  
Reservoir Computing ◽  
Multiple Time Delays ◽  
Network Topologies

We present a systematic approach to reveal the correspondence between time delay dynamics and networks of coupled oscillators. After early demonstrations of the usefulness of spatio-temporal representations of time-delay system dynamics, extensive research on optoelectronic feedback loops has revealed their immense potential for realizing complex system dynamics such as chimeras in rings of coupled oscillators and applications to reservoir computing. Delayed dynamical systems have been enriched in recent years through the application of digital signal processing techniques. Very recently, we have showed that one can significantly extend the capabilities and implement networks with arbitrary topologies through the use of field programmable gate arrays. This architecture allows the design of appropriate filters and multiple time delays, and greatly extends the possibilities for exploring synchronization patterns in arbitrary network topologies. This has enabled us to explore complex dynamics on networks with nodes that can be perfectly identical, introduce parameter heterogeneities and multiple time delays, as well as change network topologies to control the formation and evolution of patterns of synchrony. This article is part of the theme issue ‘Nonlinear dynamics of delay systems’.

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

2020 ◽  
Vol 124 ◽  
pp. 158-169 ◽  
Author(s):  
Florian Stelzer ◽  
André Röhm ◽  
Kathy Lüdge ◽  
Serhiy Yanchuk
Keyword(s):  
Time Delay ◽  
Clock Cycle ◽  
Reservoir Computing ◽  
Resonant Clock

scholarly journals Fast physical repetitive patterns generation for masking in time-delay reservoir computing

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Apostolos Argyris ◽  
Janek Schwind ◽  
Ingo Fischer
Keyword(s):  
Time Delay ◽  
Optical Feedback ◽  
Time Series Prediction ◽  
Computing System ◽  
Performance Comparison ◽  
Operating Conditions ◽  
Periodic Signal ◽  
Reservoir Computing ◽  
Temporal Masking ◽  
Fast Processing

AbstractAlbeit the conceptual simplicity of hardware reservoir computing, the various implementation schemes that have been proposed so far still face versatile challenges. The conceptually simplest implementation uses a time delay approach, where one replaces the ensemble of nonlinear nodes with a unique nonlinear node connected to a delayed feedback loop. This simplification comes at a price in other parts of the implementation; repetitive temporal masking sequences are required to map the input information onto the diverse states of the time delay reservoir. These sequences are commonly introduced by arbitrary waveform generators which is an expensive approach when exploring ultra-fast processing speeds. Here we propose the physical generation of clock-free, sub-nanosecond repetitive patterns, with increased intra-pattern diversity and their use as masking sequences. To that end, we investigate numerically a semiconductor laser with a short optical feedback cavity, a well-studied dynamical system that provides a wide diversity of emitted signals. We focus on those operating conditions that lead to a periodic signal generation, with multiple harmonic frequency tones and sub-nanosecond limit cycle dynamics. By tuning the strength of the different frequency tones in the microwave domain, we access a variety of repetitive patterns and sample them in order to obtain the desired masking sequences. Eventually, we apply them in a time delay reservoir computing approach and test them in a nonlinear time-series prediction task. In a performance comparison with masking sequences that originate from random values, we find that only minor compromises are made while significantly reducing the instrumentation requirements of the time delay reservoir computing system.

Hybrid Simulation of a Variable Transport Lag

SIMULATION ◽  
1969 ◽  
Vol 12 (2) ◽  
pp. 65-70
Author(s):  
R.N. Nilsen
Keyword(s):  
Time Delay ◽  
Execution Time ◽  
Digital Computer ◽  
Dynamic Range ◽  
Random Noise ◽  
Sampling Rate ◽  
Memory Capacity ◽  
Experimental Results ◽  
Variable Time Delay ◽  
Hybrid Solution

The object of this paper is to present a hybrid solution to the problem of simulating an ideal transport lag hav ing a variable time delay. The dynamic range over which the allowable time delay may be realized by this tech nique is limited on the low end by the sampling rate and execution time of the digital computer, and on the high end by the memory capacity of the digital computer. Experimental results using signals consisting of either sinusoidal waveforms or random noise are presented.

Sign in / Sign up

Export Citation Format

Share Document