Saved in:
Bibliographic Details
Main Authors: Mehlman, Nicholas, Gagnon-Audet, Jean-Christophe, Shvartsman, Michael, Niu, Kelvin, Miller, Alexander H., Sodhani, Shagun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.22094
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913965271941120
author Mehlman, Nicholas
Gagnon-Audet, Jean-Christophe
Shvartsman, Michael
Niu, Kelvin
Miller, Alexander H.
Sodhani, Shagun
author_facet Mehlman, Nicholas
Gagnon-Audet, Jean-Christophe
Shvartsman, Michael
Niu, Kelvin
Miller, Alexander H.
Sodhani, Shagun
contents Surface electromyography (sEMG) signals offer a promising avenue for developing innovative human-computer interfaces by providing insights into muscular activity. However, the limited volume of training data and computational constraints during deployment have restricted the investigation of scaling up the model size for solving sEMG tasks. In this paper, we demonstrate that vanilla transformer models can be effectively scaled up on sEMG data and yield improved cross-user performance up to 110M parameters, surpassing the model size regime investigated in other sEMG research (usually <10M parameters). We show that >100M-parameter models can be effectively distilled into models 50x smaller with minimal loss of performance (<1.5% absolute). This results in efficient and expressive models suitable for complex real-time sEMG tasks in real-world environments.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling and Distilling Transformer Models for sEMG
Mehlman, Nicholas
Gagnon-Audet, Jean-Christophe
Shvartsman, Michael
Niu, Kelvin
Miller, Alexander H.
Sodhani, Shagun
Audio and Speech Processing
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Surface electromyography (sEMG) signals offer a promising avenue for developing innovative human-computer interfaces by providing insights into muscular activity. However, the limited volume of training data and computational constraints during deployment have restricted the investigation of scaling up the model size for solving sEMG tasks. In this paper, we demonstrate that vanilla transformer models can be effectively scaled up on sEMG data and yield improved cross-user performance up to 110M parameters, surpassing the model size regime investigated in other sEMG research (usually <10M parameters). We show that >100M-parameter models can be effectively distilled into models 50x smaller with minimal loss of performance (<1.5% absolute). This results in efficient and expressive models suitable for complex real-time sEMG tasks in real-world environments.
title Scaling and Distilling Transformer Models for sEMG
topic Audio and Speech Processing
Artificial Intelligence
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2507.22094