当前位置: X-MOL 学术Cognit. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Limitations of the Recall Capabilities in Delay-Based Reservoir Computing Systems
Cognitive Computation ( IF 4.3 ) Pub Date : 2020-10-02 , DOI: 10.1007/s12559-020-09733-5
Felix Köster , Dominik Ehlert , Kathy Lüdge

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.



中文翻译:

基于延迟的储层计算系统中召回能力的局限性

我们以Hopf范式形式分析非线性的基于延迟的储层计算机的存储容量,并通过数值计算线性以及更高阶的召回功能。可能的物理实现方式可能是带有外腔的激光器,通过电注入为其提供信息。储层系统计算能力的与任务无关的量化是通过完整的正交函数基础函数完成的。我们的结果表明,即使对于恒定的读取尺寸,总存储容量也取决于信息输入周期(也称为时钟周期)与系统中时间延迟之间的比率。对于约1.6倍时钟周期的时间延迟,可以找到最佳性能。

更新日期:2020-10-02
down
wechat
bug