Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution

Area of Science:

• Neuroscience
• Computational Neuroscience
• Machine Learning

Background:

• Current neuroscience understanding of the brain is fragmented.
• Reading neural activity from arbitrary brain regions remains a challenge.

Purpose of the Study:

• To develop a foundation model for neural spiking data.
• To enable diverse tasks across multiple brain areas.
• To advance the understanding of neural encoding.

Main Methods:

• Introduced a novel self-supervised modeling approach: multi-task-masking (MtM).
• Model alternates between masking and reconstructing neural activity across time, neurons, and regions.
• Evaluated using the International Brain Laboratory dataset with Neuropixels recordings.

Main Results:

• MtM significantly improved performance over state-of-the-art population models.
• Enabled effective multi-task learning.
• Training on multiple animals improved generalization to unseen subjects.

Conclusions:

• The MtM approach provides a foundation for a brain-wide model at single-cell resolution.
• This work paves the way for comprehensive neural decoding.
• Future research can build upon this model for broader neuroscience applications.