R PRO

Twu31

twu3202

AI & ML interests

None yet

Recent Activity

repliedto their post about 1 hour ago

Can a Jev-style decision interface work on EEG when the questions are asked in words? In our tests, only for questions the model was trained on. A small head over frozen EEG features (encode a window once, answer several typed questions about it) was asked each question by a question number, a label template or a description. On SSVEP (BETA, 70 people), asking a seen question with a label template instead of its number cost −5.96 pp of balanced accuracy on a plain spectrum (interval −6.84 to −5.08 pp), the 2 pp margin not met. On flicker frequencies the head was never trained on, it reached 28.7%, where training-free CCA reached 80.9% (chance 12.5%). Results and limits: https://bci.report/topics/questions-in-language/ What "Jev-style" means here: https://bci.report/jev-style/ Query the numbers over MCP: https://huggingface.co/spaces/Twu31/bci-report-explorer Related write-up: https://huggingface.co/blog/Twu31/one-eeg-encoder-several-questions

updated a model about 21 hours ago

Twu31/Qwen3.6-35B-A3B-GPTQ-INT4-W4A16-LowLatency

repliedto their post about 23 hours ago

View all activity

Organizations

None yet

replied to their post about 1 hour ago

Following up on this: we ran the reference-spectrum arm (fundamental plus 2nd and 3rd harmonics, on the same 7–48 Hz bins as the EEG spectrum, everything else unchanged).

On your bet: unseen came in at 39.0%, below the 44.3% neighbour read-off and also below the numeric code's 41.5% (paired diff −2.5 pp, interval −3.5 to −1.5). CCA is still at 80.9%. On seen it landed at 31.5%, basically on top of one-hot's 32.1% (within our ±2 pp equivalence margin). CBraMod features show the same pattern.

So by your own framing the head caps both, and I'd mostly agree. I wouldn't put all of it on the head, though: a fixed template match on the same spectra, with no training, gets only 28.8% on the unseen 8-way, and CCA works on the raw multichannel signal, with timing and phase info the magnitude spectra throw away.

What would change my mind: if a stronger head, say a matching head, on the same spectra still sat near 32% on seen, I'd blame the features rather than the head. That's the obvious next thing to try. Thanks for putting a number on it.

replied to their post about 23 hours ago

Thanks for the comment! Yes, those are the plain-spectrum numbers. On frozen CBraMod features the same three arms all sit around 18–21%, so I think your ceiling point holds there too.

We didn't try the reference signal as the query. The numeric code is the closest thing we have, and it only encodes the fundamental, no harmonics.

If I had to bet, I'd say it's mostly the head: even with one-hot questions it only gets 32.1% on the seen 32-way, while CCA gets 65.5%. Honestly not sure though, and your idea is a really clean way to tell the two apart, so we'll add the reference-spectrum arm and test it. I'll post back here when we have results.

posted an update 3 days ago

Post

Before reaching for an EEG foundation model for an SSVEP speller, compare it with CCA, which needs no training at all.

BETA, 40 targets, 70 new people, eight posterior electrodes (chance 2.5%; descriptive 95% intervals in brackets): standard CCA reached 63.1% balanced accuracy (57.2–69.0%). Frozen LaBraM and CBraMod with ridge heads reached 10.8% (9.5–12.2%) and 33.7% (29.8–37.6%); EEGNet trained from scratch, 55.8% (50.1–61.3%). 16 further foundation-model checkpoints in the same frozen recipe reached at most 54.8% (49.4–60.0%), and none lies above CCA with eight electrodes or with four (57.6%). These are frozen probes with one fixed recipe, not tuned ceilings for any model.

Write-up: https://huggingface.co/blog/Twu31/cca-and-frozen-eeg-foundation-models-on-beta
Protocol, downloads and caveats: https://bci.report/protocols/beta-8ch/
Query the numbers over MCP: Twu31/bci-report-explorer

posted an update 4 days ago

Post

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

posted an update 5 days ago

Post

Can a Jev-style decision interface work on EEG when the questions are asked in words? In our tests, only for questions the model was trained on.

A small head over frozen EEG features (encode a window once, answer several typed questions about it) was asked each question by a question number, a label template or a description. On SSVEP (BETA, 70 people), asking a seen question with a label template instead of its number cost −5.96 pp of balanced accuracy on a plain spectrum (interval −6.84 to −5.08 pp), the 2 pp margin not met. On flicker frequencies the head was never trained on, it reached 28.7%, where training-free CCA reached 80.9% (chance 12.5%).

Results and limits: https://bci.report/topics/questions-in-language/
What "Jev-style" means here: https://bci.report/jev-style/
Query the numbers over MCP: Twu31/bci-report-explorer
Related write-up: https://huggingface.co/blog/Twu31/one-eeg-encoder-several-questions

4 replies

posted an update 6 days ago

Post

New write-up: when should an EEG decoder abstain?

Motivated by Jev-style typed decision interfaces; independent evaluation, not affiliated with TypeSafe, AutoTrust, ggml-org or the authors of any Jev paper.

On BETA (70 people, 40-target SSVEP, cue-paced lab trials), one calibrated threshold — accept when the top-class probability is at least 0.8 — accepted very different shares of trials: standard CCA 28.4% (95% interval 22.9–34.2%), EEGNet 16.6% (12.5–21.0%), frozen CBraMod 1.5% (0.8–2.3%), with nothing accepted at all for 38 of the 70 people under CBraMod. A learned reject option did not beat the model's own calibrated confidence, and a certified error level did not reliably hold on new people. These compare methods; they are not deployment error rates.

Article: https://huggingface.co/blog/Twu31/when-should-an-eeg-decoder-abstain
Browse or query the published figures (UI + MCP): Twu31/bci-report-explorer
Collection: Twu31/bci-report-6ac6fc80f1026c08d6cac752

BCI Report is a personal, noncommercial project; aggregate results only.

R PRO

AI & ML interests

Recent Activity

Organizations

Twu31's activity