Assembly of Echo State Networks Driven by Segregated Low Dimensional Signals
Assembly of Echo State Networks Driven by Segregated Low Dimensional Signals
复制标题
由隔离低维信号驱动的回波状态网络的组装
DOI：
10.1109/ijcnn55064.2022.9892881
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Satoshi Yamaguchi
中科院分区：
文献类型：
--
作者：
Takahiro Iinuma;Sou Nobukawa;Satoshi Yamaguchi
回声状态网络（ESN）由输入层、存储器和输出层组成，提供了比其他递归神经网络（RNN）更高的学习效率。在ESN的设计中，与输入信号的维度相比，需要足够大数量的储备神经元。因此，对于高维输入，必须增加神经元的数量以实现良好的性能。然而，神经元数量的增加增加了计算负荷。为了解决这个问题，我们提出了一个装配ESN（AESN）架构，包括一个特征提取部分，使用多个子ESN与隔离组件的高维输入和特征集成部分。为了验证所提出的AESN的有效性，我们研究和比较了传统的ESN和高维输入下的AESN。结果表明，AESN可能是上级优于传统的ESN的精度，内存性能和计算量。我们认为AESN也具有正确的整合功能。因此，该方法有望解决高维问题，提高精度。
An echo state network (ESN), consisting of an input layer, reservoir, and output layer, provides a higher learning-efficient approach than other recurrent neural networks (RNNs). In the design of ESNs, a sufficiently large number of reservoir neurons is required compared to the dimension of the input signal. Thus, the number of neurons must be increased for high-dimensional input to achieve good performance. However, an increase in the number of neurons increases the computational load. To solve this problem, we propose an assembly ESN (AESN) architecture comprising a feature extraction part that uses multiple sub-ESNs with segregated components of high-dimensional input and a feature integration part. To validate the effectiveness of the proposed AESN, we investigated and compared the conventional ESN with the AESN under high-dimensional input. The results show that the AESN is possibly superior to the conventional ESN in accuracy, memory performance, and computational load. We believe that the AESN also has a correct integration function. Therefore, the proposed method is expected to solve high-dimensional problems with improved accuracy.