.png){kind=icon}
.png){kind=icon}
Return
Reducing reservoir computer hyperparameter dependence by external timescale tailoring
.png){kind=icon}
OA
AI
DOI：10.1088/2634-4386/ad1d32.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Task specific hyperparameter tuning in reservoir computing is an open issue, and is of particular relevance for hardware implemented reservoirs. We investigate the influence of directly including externally controllable task specific timescales on the performance and hyperparameter sensitivity of reservoir computing approaches. We show that the need for hyperparameter optimisation can be reduced if timescales of the reservoir are tailored to the specific task. Our results are mainly relevant for temporal tasks requiring memory of past inputs, for example chaotic timeseries prediction. We consider various methods of including task specific timescales in the reservoir computing approach and demonstrate the universality of our message by looking at both time-multiplexed and spatially-multiplexed reservoir computing.
Keywords:
reservoir computing
hyperparameter optimisation
timeseries prediction
delay-based reservoir
Journal
IF:
6.1
Papers:
340
Citations:
920