Design Strategies for Weight Matrices of Echo State Networks
Design Strategies for Weight Matrices of Echo State Networks
复制标题
DOI：
10.1162/neco_a_00374
复制
发表时间：
2012-12-01
影响因子：
2.9
通讯作者：
Labahn, Roger
中科院分区：
文献类型：
--
作者：
Strauss, Tobias;Wustlich, Welf;Labahn, Roger
This article develops approaches to generate dynamical reservoirs of echo state networks with desired properties reducing the amount of randomness. It is possible to create weight matrices with a predefined singular value spectrum. The procedure guarantees stability (echo state property). We prove the minimization of the impact of noise on the training process. The resulting reservoir types are strongly related to reservoirs already known in the literature. Our experiments show that well-chosen input weights can improve performance.
