当前位置: X-MOL 学术Neural Process Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Finite-Time $$L_\infty $$L∞ Performance State Estimation of Recurrent Neural Networks with Sampled-Data Signals
Neural Processing Letters ( IF 2.6 ) Pub Date : 2019-11-12 , DOI: 10.1007/s11063-019-10114-9
N. Gunasekaran , M. Syed Ali , S. Pavithra

This paper, by proposing a sampled-data control scheme, we investigate the finite-time \(L_\infty \) performance state estimation of recurrent neural networks. By constructing a novel Lyapunov functional, new stability and stabilization conditions are derived. By utilizing integral inequality techniques, sufficient LMI conditions are derived to ensure the finite-time stability of considered neural networks. Furthermore, finite-time observer gain analysis of recurrent neural networks is set up to measure its disturbance tolerance capability in the fixed time interval. Numerical examples are given to verify the effectiveness of the proposed approach.

中文翻译:

带有采样数据信号的递归神经网络的有限时间$$ L_ \ infty $$L∞性能状态估计

本文通过提出一种采样数据控制方案,研究了递归神经网络的有限时间性能(L_ \ infty \)性能状态估计。通过构建新的Lyapunov泛函,得出了新的稳定性和稳定条件。通过使用积分不等式技术,可以得出足够的LMI条件,以确保所考虑的神经网络的有限时间稳定性。此外,建立了递归神经网络的有限时间观察者增益分析,以测量其在固定时间间隔内的抗干扰能力。数值算例验证了该方法的有效性。
更新日期:2019-11-12
down
wechat
bug