Department of Physics, National University of Singapore, Singapore 117551.
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore 13863.
Chaos. 2024 Aug 1;34(8). doi: 10.1063/5.0224138.
In biological neural networks, it has been well recognized that a healthy brain exhibits 1/f noise patterns. However, in artificial neural networks that are increasingly matching or even out-performing human cognition, this phenomenon has yet to be established. In this work, we found that similar to that of their biological counterparts, 1/f noise exists in artificial neural networks when trained on time series classification tasks. Additionally, we found that the activations of the neurons are the closest to 1/f noise when the neurons are highly utilized. Conversely, if the network is too large and many neurons are underutilized, the neuron activations deviate from 1/f noise patterns toward that of white noise.
在生物神经网络中，人们已经认识到健康的大脑表现出 1/f 噪声模式。然而，在越来越多的与人类认知相匹配甚至超越人类认知的人工神经网络中，这一现象尚未得到证实。在这项工作中，我们发现，与生物神经网络类似，当人工神经网络在时间序列分类任务上进行训练时，存在 1/f 噪声。此外，我们发现当神经元被高度利用时，神经元的激活最接近 1/f 噪声。相反，如果网络太大，许多神经元未被充分利用，神经元的激活则偏离 1/f 噪声模式，趋向于白噪声。
