The Conceptor network is a new framework of reservoir computing (RC), in addition to the features of easy training, global convergence, it can online learn new classes of input patterns without complete re-learning from all the training data. The conventional connection topology and weights of the hidden layer (reservoir) of RC are initialized randomly, and are fixed to be no longer fine-tuned after initialization. However, it has been demonstrated that the reservoir connection of RC plays an important role in the computational performance of RC. Therefore, in this paper, we optimize the Conceptor’s reservoir connection and propose a phase space reconstruction (PSR) -based reservoir generation method. We tested the generation method on time series prediction task, and the experiment results showed that the proposed PSR-based method can improve the prediction accuracy of Conceptor networks. Further, we compared the PSR-based Conceptor with two Conceptor networks of other typical reservoir topologies (random connected, cortex-like connected), and found that all of their prediction accuracy showed a nonlinear decline trend with increasing storage load, but in comparison, our proposed PSR-based method has the best accuracy under different storage loads.

Conceptor网络是一种新的储层计算（RC）框架，除了具有易于训练、全局收敛的特点外，它还可以在线学习新类别的输入模式，而无需从所有训练数据中完全重新学习。RC的隐藏层（reservoir）的常规连接拓扑和权重是随机初始化的，初始化后固定不再微调。然而，已经证明 RC 的储层连接在 RC 的计算性能中起着重要作用。因此，在本文中，我们优化了Conceptor 的储层连接，并提出了一种基于相空间重构（PSR）的储层生成方法。我们在时间序列预测任务上测试了生成方法，实验结果表明，所提出的基于PSR的方法可以提高Conceptor网络的预测精度。此外，我们将基于 PSR 的 Conceptor 与其他典型储层拓扑结构（随机连接、类皮质连接）的两个 Conceptor 网络进行了比较，发现它们的所有预测精度都随着存储负载的增加呈非线性下降趋势，但相比之下，我们提出的基于 PSR 的方法在不同的存储负载下具有最佳精度。