首页> 外文会议>International Joint Conference on Neural Networks >Evaluation of Information-Theoretic Measures in Echo State Networks on the Edge of Stability
【24h】

Evaluation of Information-Theoretic Measures in Echo State Networks on the Edge of Stability

机译:稳定性谐波状态网络信息 - 理论理学措施的评价

获取原文

摘要

It has been demonstrated that the computational capabilities of echo state networks are maximized when the recurrent layer is close to the border between a stable and an unstable dynamics regime, the so called edge of stability, or criticality. The maximization of performance is computationally useful, leading to minimal prediction error or maximal memory capacity, and has been shown to lead to maximization of information-theoretic measures, such as transfer entropy and active information storage in case of some datasets. In this paper, we take a closer look at these measures, using Kraskov-Grassberger-St?gbauer estimator with optimized parameters. We experiment with four datasets differing in the data complexity, and discover interesting differences, compared to the previous work, such as more complex behavior of the information-theoretic measures. We also investigate the effect of reservoir orthogonalization, that has been shown earlier to maximize memory capacity, on the prediction accuracy and the above mentioned measures.
机译:已经证明,当复制层接近稳定和不稳定的动态状态之间的边界时,回声状态网络的计算能力最大化,所谓的稳定性边缘或临界。性能的最大化是计算的,导致最小的预测误差或最大存储器容量,并且已被示出导致信息理论措施的最大化,例如在某些数据集的情况下传输熵和活动信息存储。在本文中,我们仔细研究了这些措施,使用Kraskov-Grassberger-ST?GBauer估算器具有优化参数。我们在数据复杂性中尝试不同的数据集,并与以前的工作相比,发现有趣的差异,例如信息理论措施的更复杂行为。我们还研究了储层正交化的效果,这已经表明,在预测准确性和上述措施上逐步最大化内存容量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号