Artificial neural networks learn better when they spend time not learning at all

They found that when the spiking networks were trained on a new task, but with occasional off-line periods that mimicked sleep, catastrophic forgetting was mitigated. Like the human brain, said the study authors, "sleep" for the networks allowed them to replay old memories without explicitly using old training data.

Synaptic plasticity, the capacity to be altered or molded, is still in place during sleep and it can further enhance synaptic weight patterns that represent the memory, helping to prevent forgetting or to enable transfer of knowledge from old to new tasks.

It meant that these networks could learn continuously, like humans or animals. Understanding how human brain processes information during sleep can help to augment memory in human subjects. Augmenting sleep rhythms can lead to better memory they ended.

Reference:

Ryan Golden , Jean Erik Delanois, et al, (2022, November 18), Artificial neural networks learn better when they spend time not learning at all, PLOS Computational Biology, DOI: 10.1371/journal.pcbi.1010628.