Unconventional Computation and Natural Computation - 18th International Conference, UCNC 2019, Tokyo, Japan, June 3-7, 2019, Proceedings
Unconventional Computation and Natural Computation - 18th International Conference, UCNC 2019, Tokyo, Japan, June 3-7, 2019, Proceedings
复制标题
非常规计算与自然计算 - 第 18 届国际会议，UCNC 2019，日本东京，2019 年 6 月 3-7 日，会议记录
DOI：
10.1007/978-3-030-19311-9_6
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Dale M
中科院分区：
文献类型：
--
作者：
Dale M
我们探讨了水库计算机（RC）的动态行为的结构和连接的复杂性的影响。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。使用最近提出的框架，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这些网络所表现出的行为范围。它强调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抽象行为表示的好处，而不是通过基准任务进行评估，以评估计算基板的质量，因为后者通常有偏见，并且通常对物理系统的完整计算质量没有什么了解。
We explore the effect of structure and connection complexity on the dynamical behaviour of Reservoir Computers (RC). 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 proposed 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 range of behaviours exhibited by these networks. It highlights that 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 abstract behaviour representation, rather than evaluation through benchmark tasks, to assess the quality of computing substrates, as the latter typically has biases, and often provides little insight into the complete computing quality of physical systems.