Longhorn Neurotech
Making neural-signal models small enough to run on the prosthetic itself: EMG gesture inference on a Raspberry Pi, and EEG brain-computer-interface classifiers.
Spec
- EMG input
- 8-channel, hand gestures
- EMG model
- MLP, static INT8 + ONNX
- Latency
- 0.43 ms/sample vs 1.04 ms FP32
- Hardware
- Raspberry Pi Zero 2 W
- Energy
- −45% model energy
- Accuracy cost
- 0.13 points
- EEG models
- CNN, Capsule Network
- EEG accuracy
- 60% → 80% (Optuna, Captum)
Write-up coming soon.
Why I built it
Who it was for and what problem they had.
The hard part
One decision I had to make and what I gave up.
What I'd do next
Honest limits and the next measurement.