Brain Activity Animation

Neuroprobe

Evaluating Intracranial Brain Responses to Naturalistic Stimuli

Python PyTorch License Website

Leaderboard

Rank Model SS/SM SS/DM DS/DM Overall
1 Linear Lite 0.591 0.562 --- ---
2 BrainBert Lite 0.575 0.562 --- ---
3 PopT 0.547 0.545 0.507 0.533
Rank Model SS/SM SS/DM DS/DM Overall
1 Linear 0.534 0.527 0.507 0.523

About

Abstract

We present Neuroprobe, a benchmark for understanding how the brain processes information across multiple tasks. Neuroprobe analyzes intracranial recordings during naturalistic stimuli using techniques from modern natural language processing. By probing neural responses across many tasks simultaneously, Neuroprobe aims to reveal the functional organization of the brain and relationships between different cognitive processes.

Paper

Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli

By Andrii Zahorodnii¹²*, Bennett Stankovits¹*, Christopher Wang¹*, Charikleia Moraitaki¹, Geeling Chau³, Ila R Fiete¹², Boris Katz¹, Andrei Barbu¹

¹MIT CSAIL, CBMM | ²MIT McGovern Institute | ³Caltech | *Equal contribution

Citation

If you use Neuroprobe in your work, please cite our paper:

@misc{2024neuroprobe,
  title={Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli},
  author={Zahorodnii, Andrii and Stankovits, Bennett and Wang, Christopher and Moraitaki, Charikleia and Chau, Geeling and Fiete, Ila R and Katz, Boris and Barbu, Andrei},
  year={2025},
  publisher={TBD},
  url={TBD}
}