Reservoir computing quality: connectivity and topology
Reservoir computing quality: connectivity and topology
复制标题
DOI：
10.1007/s11047-020-09823-1
复制
发表时间：
2020-12-15
影响因子：
2.1
通讯作者：
Trefzer, Martin A.
中科院分区：
文献类型：
--
作者：
Dale, Matthew;O'Keefe, Simon;Trefzer, Martin A.
我们探讨了连通性和拓扑结构对水库计算机动态行为的影响。目前，在设计和手工制作物理储层计算机方面付出了相当大的努力。结构和物理复杂性往往是关键的任务性能，然而，评估其整体的重要性是具有挑战性的。使用最近开发的框架，我们评估和比较神经网络结构的动态自由度（指质量），作为物理系统的类比。结果量化了结构如何影响网络的行为范围。它展示了更复杂结构所达到的高质量通常也可以在具有更大网络尺寸的更简单结构中实现。或者，在较小的网络中，通常通过增加更大的连接复杂性来提高质量。这项工作证明了使用动态行为来评估计算基板的质量的好处，而不是通过基准任务进行评估，这些基准任务通常提供对物理系统的计算质量的狭隘和有偏见的见解。
We explore the effect of connectivity and topology on the dynamical behaviour of Reservoir Computers. At present, considerable effort is taken to design and hand-craft physical reservoir computers. Both structure and physical complexity are often pivotal to task performance, however, assessing their overall importance is challenging. Using a recently developed framework, we evaluate and compare the dynamical freedom (referring to quality) of neural network structures, as an analogy for physical systems. The results quantify how structure affects the behavioural range of networks. It demonstrates how high quality reached by more complex structures is often also achievable in simpler structures with greater network size. Alternatively, quality is often improved in smaller networks by adding greater connection complexity. This work demonstrates the benefits of using dynamical behaviour to assess the quality of computing substrates, rather than evaluation through benchmark tasks that often provide a narrow and biased insight into the computing quality of physical systems.