How noise affects memory in linear recurrent networks
This work addresses the problem of understanding noise effects on memory in neural networks for researchers in computational neuroscience and AI.
The study investigated how noise impacts memory in linear recurrent networks, finding that memory reduction is determined by the noise's power spectral density and that memory remains stable under certain noise distributions, with results validated using human brain signals.
The effects of noise on memory in a linear recurrent network are theoretically investigated. Memory is characterized by its ability to store previous inputs in its instantaneous state of network, which receives a correlated or uncorrelated noise. Two major properties are revealed: First, the memory reduced by noise is uniquely determined by the noise's power spectral density (PSD). Second, the memory will not decrease regardless of noise intensity if the PSD is in a certain class of distribution (including power law). The results are verified using the human brain signals, showing good agreement.