Department of Physics, The Ohio State University, 191 W. Woodruff Ave., Columbus, Ohio 43210, USA.
Potomac Research LLC, 801 N. Pitt St. # 117, Alexandria, Virginia 22314, USA.
Chaos. 2019 Dec;29(12):123108. doi: 10.1063/1.5120710.
We explore the hyperparameter space of reservoir computers used for forecasting of the chaotic Lorenz '63 attractor with Bayesian optimization. We use a new measure of reservoir performance, designed to emphasize learning the global climate of the forecasted system rather than short-term prediction. We find that optimizing over this measure more quickly excludes reservoirs that fail to reproduce the climate. The results of optimization are surprising: the optimized parameters often specify a reservoir network with very low connectivity. Inspired by this observation, we explore reservoir designs with even simpler structure and find well-performing reservoirs that have zero spectral radius and no recurrence. These simple reservoirs provide counterexamples to widely used heuristics in the field and may be useful for hardware implementations of reservoir computers.
我们使用贝叶斯优化探索了用于预测混沌 Lorenz '63 吸引子的储层计算机的超参数空间。我们使用了一种新的储层性能度量方法，旨在强调学习预测系统的全局气候，而不是短期预测。我们发现，使用这种度量方法进行优化可以更快地排除那些无法再现气候的储层。优化的结果令人惊讶：优化后的参数通常指定一个具有非常低连通性的储层网络。受此观察结果的启发，我们探索了具有更简单结构的储层设计，并找到了性能良好的储层，它们的谱半径为零，没有递归。这些简单的储层为该领域中广泛使用的启发式方法提供了反例，并且可能对储层计算机的硬件实现有用。
