A substrate-independent framework to characterize reservoir computers
A substrate-independent framework to characterize reservoir computers
复制标题
DOI：
10.1098/rspa.2018.0723
复制
发表时间：
2019-06-01
影响因子：
3.5
通讯作者：
Trefzer, Martin A.
中科院分区：
文献类型：
--
作者：
Dale, Matthew;Miller, Julian F.;Trefzer, Martin A.
储层计算（RC）框架指出，任何非线性的、输入驱动的动力系统（储层）都具有诸如衰落记忆和输入可分性等特性，可以通过训练来执行计算任务。这种广泛的系统包含导致了许多新的物理基材RC。储层计算所需的基本属性可以通过基板的重新配置来调整，例如虚拟拓扑或物理形态的变化。因此，通过重新配置，每种基质都具有独特的“品质”，以实现不同任务的不同储层。在这里，我们描述了一个实验框架，以表征潜在的任何基材RC的质量。我们的框架揭示了质量的定义不仅对比较底物有用，而且可以帮助映射属性和任务性能之间的重要关系。在更广泛的背景下，该框架提供了一个更好的理解是什么使动力系统的计算，有助于改进设计未来的基板RC。
The reservoir computing (RC) framework states that any nonlinear, input-driven dynamical system (the reservoir) exhibiting properties such as a fading memory and input separability can be trained to perform computational tasks. This broad inclusion of systems has led to many new physical substrates for RC. Properties essential for reservoirs to compute are tuned through reconfiguration of the substrate, such as change in virtual topology or physical morphology. As a result, each substrate possesses a unique 'quality'-obtained through reconfiguration-to realize different reservoirs for different tasks. Here we describe an experimental framework to characterize the quality of potentially any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can help map the non-trivial relationship between properties and task performance. In the wider context, the framework offers a greater understanding as to what makes a dynamical system compute, helping improve the design of future substrates for RC.