2026-05-17

2-M16 electrode ablation study

A new exploratory ablation retrains the featured 2-M16 recipe with different Muse 2 channel subsets to estimate which electrodes carry the most subject-specific action and finger information.

Historical note: archived update posts preserve the figures published at that time. For the current verified run bundles, use the results page.

What changed

The site now includes an electrode ablation report for the featured 2-M16 recipe. The study retrains the model after changing which Muse 2 channels are available, then compares held-out action accuracy and non-REST finger accuracy.

This is a subject-specific retraining ablation. It is not yet deployment-gated replay, and it should not be read as anatomical localization.

The report is now included near the bottom of the deep dive.

Study setup

ItemValue
Branchablation/electrode-channel-importance
Train/test configSame featured 2-M16 derived dataset, split policy, model recipe, and deterministic test evaluation
Primary sweepSeed 43, 60 epochs
SubsetsFull montage, single-channel, leave-one-out
Additional runTP9+TP10 only, dropping both AF7 and AF8

The fresh full-montage retrain reached 90.96% action accuracy and 86.26% non-REST finger accuracy. It is close to the locked paper checkpoint, but it is a new training run and should be compared only against the ablation runs in this sweep.

Headline result

ChannelsAction accuracyNon-REST finger accuracyAction drop vs fullFinger drop vs full
TP9+AF7+AF8+TP1090.96%86.26%0.00 pp0.00 pp
TP9+TP10 only88.31%83.90%2.65 pp2.36 pp

Removing both frontal electrodes preserves most of the full-montage retrain. That supports the working hypothesis that, for this subject and split, the most useful signal is concentrated in the temporal electrodes TP9 and TP10.

Leave-one-out importance

Omitted electrodeKept channelsAction drop vs fullFinger drop vs full
TP10TP9+AF7+AF812.08 pp9.13 pp
TP9AF7+AF8+TP1011.73 pp13.29 pp
AF7TP9+AF8+TP101.13 pp-0.40 pp
AF8TP9+AF7+TP100.56 pp-1.30 pp

TP9 and TP10 are the important leave-one-out channels in this sweep. Dropping AF7 or AF8 causes little action degradation and slightly improves aggregate finger accuracy.

Single-channel sufficiency

ElectrodeAction accuracyNon-REST finger accuracy
TP973.01%72.22%
TP1072.66%67.80%
AF748.89%35.46%
AF848.33%36.16%

TP9 and TP10 each retain substantial information alone. AF7 and AF8 perform much closer to weak single-channel models.

Frontal-channel action behavior

Dropping a frontal electrode did not reduce REST accuracy.

RunREST deltaOPEN deltaCLOSE delta
Drop AF7+0.65 pp-2.39 pp-0.56 pp
Drop AF8+2.28 pp-3.37 pp+1.03 pp

The small action decrease from frontal-channel removal is mainly an OPEN decrease. It is not a REST failure and not a uniform action decrease.

Per-finger behavior

RunOverall deltaTHUMBINDEXMIDDLERINGPINKY
Drop AF7+0.40 pp+0.00 pp-7.95 pp-3.16 pp+12.60 pp+0.51 pp
Drop AF8+1.30 pp+0.00 pp-2.45 pp-1.81 pp+18.90 pp-6.87 pp
TP9+TP10 only-2.36 pp-0.43 pp-15.29 pp-10.38 pp+12.33 pp+1.53 pp

The frontal channels may still help specific digit boundaries, especially INDEX and MIDDLE. They may also add noise or conflicting information for RING in this subject-specific split.

Current interpretation

The ablation supports three practical conclusions:

  • TP9 and TP10 are the strongest channel candidates for this subject-specific model.
  • AF7 and AF8 are not required to preserve most held-out accuracy in this single-seed retraining sweep.
  • Reduced-channel command-path claims still require repeated seeds and deployment-consistent replay.

The next validation step is to repeat the channel sweep across seeds, then replay the strongest reduced montages through the same conservative command gates used before robotic-hand actuation.