.png){kind=icon}
返回
Reducing reservoir computer hyperparameter dependence by external timescale tailoring
.png){kind=icon}
OA
AI
DOI：10.1088/2634-4386/ad1d32.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
reservoir computing
hyperparameter optimisation
timeseries prediction
delay-based reservoir
期刊
IF:
6.1
论文数:
340
被引数:
920
机构
引用论文
A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏分享收藏分享收藏分享收藏Performance boost of time-delay reservoir computing by non-resonant clock cycleNEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容