NeuroLens improves decoding of brain signals over long times in mice and humans
NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings
Machine Learning
Summary
It's hard to tell if changes in brain recordings over days are due to learning or simply noise from the recording process. The authors created NeuroLens, a model that finds stable patterns in brain activity by predicting future brain states and reducing noise. This helps better understand how brain activity relates to decisions and meaning, even when recordings change over time. NeuroLens works in mice and humans and quickly adapts to new brain data.
What this means in practice
- •For brain-computer interface developers: Create neural decoding systems that retain accuracy across multiple days despite recording variability and changing neural populations.$Commercial implications: Enables more reliable, long-term brain-computer interfaces for communication and control, improving commercial BCI devices.
- •For neurotechnology research engineers: Develop algorithms to analyze chronic neural recordings with greater stability and semantic understanding of neural signals.
Authors
Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie, Anne Churchland, Liam Paninski, Yizi Zhang
Abstract
Understanding how neural activity represents higher-order cognition and how these representations evolve over time has long been a central pursuit in neuroscience. However, current analytical tools cannot easily distinguish representational plasticity from recording instability in chronic neural recordings. Here, we introduce NeuroLens (Latent Embeddings of Neural Semantics), a self-supervised model based on the Joint-Embedding Predictive Architecture (JEPA) framework that learns denoised, semantically informative latents from chronic neural recordings. An adaptive encoder maps changing neural populations into a common latent space, while a temporal predictor learns structure that supports prediction of future latent states. By predicting in latent space, NeuroLens captures temporally predictable structure and reduces sensitivity to transient, recording-specific variability. Across chronic intracortical data in mice and humans, the learned representations improve decoding of decision-making and semantic task variables. Multi-day pretraining enables generalization to future sessions, rapid few-shot adaptation to unseen neural populations, and more stable decoding over time than state-of-the-art baselines. Together, these results establish NeuroLens as a new paradigm for studying how neural representations change during learning and over long timescales.