School of Mathematical Sciences, University College Cork, Cork T12 XF62, Ireland.
Raytheon Technologies Research Center Ireland, Cork T23 XN53, Ireland.
Chaos. 2021 Jan;31(1):013125. doi: 10.1063/5.0019974.
Multifunctionality is a well observed phenomenological feature of biological neural networks and considered to be of fundamental importance to the survival of certain species over time. These multifunctional neural networks are capable of performing more than one task without changing any network connections. In this paper, we investigate how this neurological idiosyncrasy can be achieved in an artificial setting with a modern machine learning paradigm known as "reservoir computing." A training technique is designed to enable a reservoir computer to perform tasks of a multifunctional nature. We explore the critical effects that changes in certain parameters can have on the reservoir computers' ability to express multifunctionality. We also expose the existence of several "untrained attractors"; attractors that dwell within the prediction state space of the reservoir computer were not part of the training. We conduct a bifurcation analysis of these untrained attractors and discuss the implications of our results.
多功能性是生物神经网络中一个被广泛观察到的现象学特征，被认为对某些物种的生存具有重要意义。这些多功能神经网络能够在不改变任何网络连接的情况下执行多项任务。在本文中，我们研究了如何在一种被称为“储层计算”的现代机器学习范例中，在人工环境中实现这种神经特质。我们设计了一种训练技术，使储层计算机能够执行多功能任务。我们探讨了某些参数变化对储层计算机表达多功能性能力的关键影响。我们还揭示了存在多个“未训练吸引子”；这些吸引子位于储层计算机的预测状态空间内，不属于训练的一部分。我们对这些未训练吸引子进行了分岔分析，并讨论了我们的结果的意义。
