Post
77
Before deciding how much of an EEG foundation model to fine-tune, check how strong its frozen readout already is.
LaBraM Base on mental arithmetic vs rest (EEGMAT, 36 new people, no labels from the test person, three seeds; descriptive 95% intervals in brackets): updating the last block reached 65.7% balanced accuracy (61.6–69.7%) and rank-4 LoRA 64.1% (60.2–67.8%), against 56.6% (54.2–59.0%) for a short head-only fit. A frozen encoder with a ridge readout, published separately on the same people and folds, reached 64.6% (60.5–68.6%): a different head, not a paired comparison. LoRA minus last block was −1.6 pp (−4.4 to +1.0), so no ordering. And LoRA, with 38,802 trainable parameters against 482,882, took about 128 s to train against 65 s (15 fits each, one Apple-silicon Mac, this implementation).
Write-up: https://huggingface.co/blog/Twu31/choosing-how-to-adapt-an-eeg-foundation-model
Results and limits: https://bci.report/topics/model-adaptation/
Query the numbers over MCP: Twu31/bci-report-explorer
LaBraM Base on mental arithmetic vs rest (EEGMAT, 36 new people, no labels from the test person, three seeds; descriptive 95% intervals in brackets): updating the last block reached 65.7% balanced accuracy (61.6–69.7%) and rank-4 LoRA 64.1% (60.2–67.8%), against 56.6% (54.2–59.0%) for a short head-only fit. A frozen encoder with a ridge readout, published separately on the same people and folds, reached 64.6% (60.5–68.6%): a different head, not a paired comparison. LoRA minus last block was −1.6 pp (−4.4 to +1.0), so no ordering. And LoRA, with 38,802 trainable parameters against 482,882, took about 128 s to train against 65 s (15 fits each, one Apple-silicon Mac, this implementation).
Write-up: https://huggingface.co/blog/Twu31/choosing-how-to-adapt-an-eeg-foundation-model
Results and limits: https://bci.report/topics/model-adaptation/
Query the numbers over MCP: Twu31/bci-report-explorer