We demonstrate that matching the symmetry properties of a reservoir computer (RC) to the data being processed can dramatically increase its processing power. We apply our method to the parity task, a challenging benchmark problem, which highlights the benefits of symmetry matching. Our method outperforms all other approaches on this task, even artificial neural networks (ANN) hand crafted for this problem. The symmetry-aware RC can obtain zero error using an exponentially reduced number of artificial neurons and training data, greatly speeding up the time-to-result. We anticipate that generalizations of our procedure will have widespread applicability in information processing with ANNs.

翻译：我们证明,将储油层计算机(RC)的对称性与正在处理的数据相匹配,可以大大提高其处理能力。我们运用我们的方法来完成对称性任务,这是一个具有挑战性的基准问题,凸显了对称性匹配的好处。我们的方法比这项任务上所有其他方法都好,甚至人工神经网络(ANN)也是为此问题手工设计的。对称性识RC可以使用人造神经元和培训数据数量成倍减少来获得零误差,大大加快了时间到结果的速度。我们预计,我们程序的一般化将在与ANN的信息处理中具有广泛的适用性。