Since the definition of \(p\)-mean almost periodic functions on time scales occupies a fundamental position in studying \(p\)-mean almost periodicity for stochastic neural networks, a concept of \(p\)-mean almost periodic functions on an invariant under a translation time scale is introduced for the first time in this paper. As an application, the existence and exponential stability of piecewise mean-square almost periodic solutions for a class of high-order BAM neural networks on time scales is studied by using the contraction mapping principal and differential inequality techniques. Finally, a numerical example is presented to illustrate the feasibility of our main results.

中文翻译：

---

转换时间尺度下不变性上的脉冲随机BAM神经网络

自定义\（P \） -mean时间尺度上几乎周期函数占用学习的基本位置\（P \） -mean几乎周期性的随机神经网络的概念\（P \） -mean概周期函数本文首次介绍了翻译时间尺度下的不变量。作为应用，利用收缩映射原理和微分不等式技术研究了一类高阶BAM神经网络在时间尺度上的分段均方几乎周期解的存在性和指数稳定性。最后，通过数值例子说明了我们主要结果的可行性。