Skip to main content

​
Evidence

Figures and tables below come from two exploratory manuscripts:
  1. Universal Personalizer — Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models (Paper 1)
  2. Resource Ladder — When Should a Deployed BCI Decoder Spend Adaptation Resources? A Resource Ladder for Frozen Encoders (Paper 1b)
All numbers are exploratory, protocol-local, and locked to the evaluation suite CSVs. Do not treat them as suite-wide constants. Headline (Paper 1): ship one Personalizer; treat fine-tune as a priced escape hatch. Use the head where capacity exists; stay cal-only when clean wins. Labels L0 / L1 / LP / L2 / L3 — see the plain-language legend. Shipped path = L0/L1; LP is a bench control; L2 is protocol/bench (affine); L3 is the FT hatch.

​
How the experiments work (data flow)

Before the numbers: this is the shared Paper 1 / 1b experimental pipeline. Experimental pipeline: datasets → preprocess → sessions → freeze encoder → optional channel-mix stress → embeddings → personalization → score Papers 1 & 1b — end-to-end data flow. Calibration stays clean; synthetic stress hits adaptation and evaluation EEG only. Not claimed as covered by this stress: physical electrode displacement, SNR drop, or every clinical shift type — only controlled synthetic channel mixing.

​
Core: L0 / Bayesian head / linear probe / full FT

Main multi-trunk accuracy–cost block (Paper 1): under the same transfer cells (severe channel-mix stress, n=40, CUDA), calibration-only Personalizer (L0), stream Personalizer (L1), a matched linear probe on the same frozen embeddings, and warm-start full fine-tune (L3). Core: L0 / Bayesian head / linear probe / full FT (severe · n=40) Paper 1 — top: L0 / L1 / linear probe / L3 accuracy; blue rec labels = (acc_L1 − acc_L0) / (acc_L3 − acc_L0), or “≥FT” when L1 matches or beats L3. Bottom: adapt fit wall (L0 stream wall = 0) with L3/L1 ratios. Recovery = (acc_L1 − acc_L0) / (acc_L3 − acc_L0). On most trunks the Bayesian head recovers ~65–90% of the FT gain over cal-only and beats the matched probe (EEGNet / Deep / Conformer). Shallow and ATCNet are probe-competitive (LP can edge L1 by a few points) while both stay far below L3 wall — Personalizer remains the product default (same API + UQ / BrainState), not a claim that L1 always wins raw accuracy. BNCI Shallow is still the Pareto win vs FT (~2× wall); ATCNet on BNCI is the hatch case (8% recovery). Mid severity strengthens “head first”: across BNCI+Zhou subject cells, stream L1 matches or beats warm-start L3 on accuracy in about half of cells at severity 0.25 / 0.5 (~49% / ~48%) versus about a third at 0.75 (~35%). Wall L3/L1 ratios stay expensive at every severity — severe is where FT most often still buys residual pp.

​
Which head? (LDA vs QDA vs Softmax)

The multi-trunk map locks LDA for comparability. On the EEGNet path, Paper 1 also compares QDA and Softmax under the same bake-off geometry (severe and clean, n=40). EEGNet Personalizer head family: LDA vs QDA vs Softmax under severe shift Paper 1 — top: accuracy (Δacc vs LDA). Bottom: adapt fit wall with mean utility labels.
  • Product default: LDA (head="lda") — no optional dependency; locked ladder / FT narrative.
  • BNCI severe: QDA lifts utility (~+0.085–0.088) at essentially the same wall; Softmax gains accuracy but pays ~1.7× LDA wall.
  • Zhou severe (n=4): inconclusive — QDA / Softmax at or below LDA. Clean BNCI/Zhou: heads nearly tied on U.
  • Softmax stays optional (nimbus-bci[softmax]) for UQ-oriented deployments. The 18-cell transfer map is not re-run for every head.
API knobs: Encoder contract.

​
More evidence

Stream Personalizer (L1) vs calibration-only (L0) across synthetic channel-mix stress levels on an 18-cell trunk×dataset map:Personalizer head across severities: cells with positive L1−L0 utility and per-dataset mean gainPaper 1 — mid shift already recovers; severe is a detailed slice, not the only supporting point. Kumar stays near zero (boundary).At severity 0.75, which ladder level wins by mean utility (L0 / L1 / L2 protocol affine+head — L2 is bench-only):Zhou: head helps on every trunk. BNCI: often useful, not automatic (ATCNet stays L0). Kumar/Shin: boundaries — Personalizer is the default integration path, not a guarantee that L1 beats L0 everywhere.
Controlled bake-off on one classical reference trunk (BNCI primary, Paper 1b). Under severe shift with n=40 labeled stream trials, the Bayesian head can beat full FT on BNCI in this protocol; Zhou is the honest softer boundary.BNCI2014-004 cost bake-off: Bayesian head accuracy vs adaptation fit time compared to frozen, linear probe, LoRA, last-layer FT, and full FTPaper 1b — BNCI2014-004, severity 0.75, n=40 (mean over 9 subjects).Recovery = Δacc / Δacc_fullFT (values > 1 mean the head beats FT). Treat head-beats-FT as BNCI-primary in this protocol, not a suite-wide constant. On Zhou2016 (supporting, 4 subjects): frozen 0.317 → head 0.462 → full FT 0.540 (~0.43× of FT gain at ~5.5× lower fit time).Paper 1 EEGNet arm zoo (same denser grammar; bake-off walls ~5× ≠ ladder CUDA L3/L1 ~20–30×):EEGNet denser baselines from the cost bake-off (severe · n=40)
The same Personalizer contract runs on Hub REVE. Under severe shift, adapt wall stays sub-second while last-layer / full FT cost about 20×–40× more on Zhou/Kumar.REVE Personalizer versus short fine-tune: Δacc and adapt fit time on Zhou and KumarPaper 1 — REVE severe n=40; accuracy × price.
  • Kumar: head Pareto-dominates short FT (+5.8 pp vs last +5.1 pp at far lower wall).
  • Zhou: last-layer can buy extra pp (+13 vs head +4.7) at ~21× wall — priced purchase, not the default.
  • Not claimed: frozen REVE + Personalizer matches cal-trained EEGNet absolute accuracy. BNCI REVE cost is a 3-subject smoke — not a headline.
Soft operational default vs strict ordinal schedule (18 cells; exploratory). “Severe → L2” means the protocol affine+head winner — not a shipped Personalizer API call.Transfer map for the Personalizer adaptation ladder across 18 trunk×dataset cellsPaper 1 — cal-only-when-clean transfers often (12/18); strict ordinal (clean→L0 and severe→L2) is conditional (5/18) — boundary, not the product headline.

​
Product claim (honest boundaries)

Not claimed: L1 always beats L0 or LP; QDA always beats LDA; universal ordinal severity→level law; coverage of session / electrode / SNR shift (evidence is synthetic channel mixing); foundation SOTA; suite-wide 30× ratios from other protocols; shipped “Active Inference for EEG”; shipped affine map (L2) as a Personalizer API.

​
Next Read

Overview

Encoder contract

BrainState

Python Quickstart