Széliga María I, Verdes Pablo F, Granitto Pablo M, Ceccatto H Alejandro
Instituto de Física Rosario, Consejo Nacional de Investigaciones Científicas y Técnicas and Universidad Nacional de Rosario, Boulevard 27 de Febrero 210 Bis, 2000 Rosario, Argentina.
Int J Neural Syst. 2003 Apr;13(2):103-9. doi: 10.1142/S0129065703001492.
We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.
我们对之前提出的一种用于学习时间序列中迫使非平稳行为的隐藏信号的人工神经网络方法进行了改进和补充。该方法在网络中添加了一个额外的输入单元，并为其提供未知扰动信号的提议轮廓。这个新输入参数的正确时间演化与序列背后的内在平稳动力学同时学习，这是通过在训练过程中最小化一个适当定义的误差函数来实现的。我们在此纳入了使用从训练集中留出的验证数据，以准确确定该方法所需超参数的最优值。此外，我们在可控情况下评估了该算法，并表明它优于文献中其他现有方法。最后，我们讨论了对实际太阳黑子时间序列的初步应用，并将获得的隐藏扰动信号与太阳磁场的长期演化联系起来。
