论文标题
探索不同储层计算机多功能的极限
Exploring the limits of multifunctionality across different reservoir computers
论文作者
论文摘要
多功能神经网络能够执行多个任务而无需更改任何网络连接。在本文中，我们探讨了连续时间，泄漏综合器和下一代“储层计算机”（RC）的性能，当时在测试多功能性限制的任务进行培训时。在第一个任务中，我们训练每个RC以重建来自不同动力学系统的混沌吸引子共存。通过将描述这些吸引子描述的数据更加靠近，我们发现每个RC在开始重叠在状态空间中时都可以重建两个吸引子的程度。为了更了解这种抑制作用，在第二任任务中，我们训练每个RC以重建两个圆形轨道的共存，这仅在旋转方向上有所不同。我们研究了在这种完全重叠的训练数据的极端情况下，每个RC中某些参数可以实现多功能性的关键效果。
Multifunctional neural networks are capable of performing more than one task without changing any network connections. In this paper we explore the performance of a continuous-time, leaky-integrator, and next-generation `reservoir computer' (RC), when trained on tasks which test the limits of multifunctionality. In the first task we train each RC to reconstruct a coexistence of chaotic attractors from different dynamical systems. By moving the data describing these attractors closer together, we find that the extent to which each RC can reconstruct both attractors diminishes as they begin to overlap in state space. In order to provide a greater understanding of this inhibiting effect, in the second task we train each RC to reconstruct a coexistence of two circular orbits which differ only in the direction of rotation. We examine the critical effects that certain parameters can have in each RC to achieve multifunctionality in this extreme case of completely overlapping training data.
