CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
📰 ArXiv cs.AI
Learn how to adapt large pretrained scalp-EEG foundation models to intracranial electrocorticography (ECoG) for cross-patient learning and competitive decoding performance
Action Steps
- Investigate the use of large pretrained scalp-EEG foundation models (EEG FMs) for intracranial electrocorticography (ECoG)
- Adapt EEG FMs to ECoG using transfer learning techniques
- Evaluate the performance of adapted models on ECoG data
- Compare the results with subject-specific decoders
- Apply the adapted models to enable cross-patient learning and competitive decoding performance
Who Needs to Know This
Neuroscientists, AI engineers, and researchers working on brain-computer interfaces can benefit from this knowledge to improve decoding performance and enable cross-patient learning
Key Insight
💡 Large pretrained scalp-EEG foundation models can be adapted to intracranial ECoG for cross-patient learning and competitive decoding performance
Share This
🧠 Adapt large pretrained scalp-EEG models to intracranial ECoG for improved decoding performance #CORTEG #braincomputerinterfaces
Key Takeaways
Learn how to adapt large pretrained scalp-EEG foundation models to intracranial electrocorticography (ECoG) for cross-patient learning and competitive decoding performance
Full Article
Title: CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
Abstract:
arXiv:2605.10337v1 Announce Type: new Abstract: Intracranial electrocorticography (ECoG) offers high-signal-to-noise access to cortical activity for brain-computer interfaces, yet limited per-patient data has led most prior work to rely on small, subject-specific decoders that neglect information shared across patients. We investigate whether large pretrained scalp-EEG foundation models (EEG FMs) can be adapted to ECoG, enabling cross-patient learning and competitive decoding performance while c
Abstract:
arXiv:2605.10337v1 Announce Type: new Abstract: Intracranial electrocorticography (ECoG) offers high-signal-to-noise access to cortical activity for brain-computer interfaces, yet limited per-patient data has led most prior work to rely on small, subject-specific decoders that neglect information shared across patients. We investigate whether large pretrained scalp-EEG foundation models (EEG FMs) can be adapted to ECoG, enabling cross-patient learning and competitive decoding performance while c
DeepCamp AI