基于层次化可塑性回声状态网络的混沌时间序列预测

为了提高回声状态网络对于混沌时间序列特征提取与预测的能力,提出一种层次化可塑性回声状态网络模型.该模型将多个储备池顺序连接,通过逐层特征变换的方式增强对非线性多尺度动态特征的提取能力.同时,引入神经科学中的内在可塑性机制模拟真实生物神经元的放电率分布,以最大化神经元的信息传递为目标对储备池进行预训练.层次化可塑性回声状态网络不仅能够增加模型的容量,降低随机投影所带来的不稳定性,而且也为理解储备池的表示、处理、记忆及储存操作提供一种新的思路.仿真实验结果表明,相比于其他7种改进的回声状态网络模型,所提出的模型在人造数据和真实数据所构成的混沌时间序列预测任务中均能取得最优的预测精度.

Hierarchical plasticity echo state network for chaotic time series prediction

To improve the ability of echo state network for feature extraction and prediction on chaotic time series, a hierarchical plasticity echo state network(HPESN) model is proposed. In this model, multiple reservoirs are connected in sequence, and the ability of nonlinear multi-scale dynamic feature extraction is enhanced through layer-by-layer feature transformation. Meanwhile, the intrinsic plasticity mechanism in neuroscience is introduced to simulate the firing rate distribution of real biological neurons, and the reservoir is pre-trained with the goal of maximizing neuronal information transmission. The HPESN not only increases the capacity of the model and reduces the instability caused by random projection, but also provides a new idea for understanding the representation, processing, memory and storage operations of the reservoir. The simulation results show that compared with other seven modified echo state network models, the proposed HPESN model achieves the best prediction accuracy in the chaotic time series prediction task composed of synthetic data and real-world data.