On April 17, the research group led by Professor Liu Yunzhe from the State Key Laboratory of Cognitive Neuroscience and Learning, the IDG/McGovern Institute for Brain Research, Beijing Normal University, and the Chinese Institute for Brain Research, published an online paper entitled "Interpreting Human Sleep Activity Through Neural Contrastive Learning" in Neuron. This study further advances the deep integration of artificial intelligence and brain science, enabling researchers not only to determine whether a person is asleep and which stage of sleep they are in, but also to begin interpreting the contents of cognitive processing during sleep. The findings provide a new research foundation for memory enhancement, the regulation of abnormal memories, interventions for sleep-related brain disorders, and the objective evaluation of dream content.

The Summary of the paper is as follows:

Spontaneous memory replay during sleep is crucial for cognition but challenging to capture because distinct sleep rhythms hinder the generalization of wake-trained electroencephalogram (EEG) decoders. To address this, we developed the Sleep Interpreter (SI), which uses neural contrastive learning to isolate shared semantic content from background rhythms. We collected a dataset of 135 participants undergoing targeted reactivation of 15 semantic categories, yielding approximately 1,000 h of overnight sleep and 400 h of wake EEG. During non-rapid eye movement (NREM) sleep, SI achieved high decoding accuracy for cue-evoked semantic responses, with accuracy peaking during slow oscillation and spindle coupling at 40.02% top-1 accuracy on unseen participants (chance 6.7%). We demonstrated SI generalizability in two independent nap experiments involving targeted and spontaneous reactivation, where decoded reactivations correlated with post-sleep memory performance. Finally, we implemented SI for real-time sleep staging and stage-specific NREM and REM decoding. The dataset and codebase are shared as open resources for future clinical applications.

Reference: https://www.cell.com/neuron/fulltext/S0896-6273(26)00219-9