Abstract Recurrent neural networks are designed to be convergent to the desired equilibrium point for their applications. Network parameter variations lead network states to other different points. So this paper discusses the prescribed convergence problem of recurrent neural networks with parameter variations. Firstly, we recurrent neural networks’ equilibrium point variation principles when parameters are changed. Then we design one track controller to make recurrent neural networks be convergent to the prescribed equilibrium for known parameter variations. Next, we present one adaptive controller to lead network states to the desired equilibrium for unknown parameter variations. At last, two examples are given for validating the presented methods.

中文翻译：

---

具有参数变化的循环神经网络的规定收敛分析

摘要 循环神经网络被设计为收敛到其应用所需的平衡点。网络参数变化导致网络状态到其他不同点。因此本文讨论了具有参数变化的递归神经网络的规定收敛问题。首先，我们在参数改变时递归神经网络的平衡点变化原理。然后我们设计了一个跟踪控制器，使循环神经网络收敛到已知参数变化的规定平衡。接下来，我们提出了一种自适应控制器，用于将网络状态引导到未知参数变化的所需平衡。最后，给出了两个例子来验证所提出的方法。