Cargando…
Using adversarial networks to extend brain computer interface decoding accuracy over time
Existing intracortical brain computer interfaces (iBCIs) transform neural activity into control signals capable of restoring movement to persons with paralysis. However, the accuracy of the ‘decoder’ at the heart of the iBCI typically degrades over time due to turnover of recorded neurons. To compen...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
eLife Sciences Publications, Ltd
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10446822/ https://www.ncbi.nlm.nih.gov/pubmed/37610305 http://dx.doi.org/10.7554/eLife.84296 |
_version_ | 1785094406741688320 |
---|---|
author | Ma, Xuan Rizzoglio, Fabio Bodkin, Kevin L Perreault, Eric Miller, Lee E Kennedy, Ann |
author_facet | Ma, Xuan Rizzoglio, Fabio Bodkin, Kevin L Perreault, Eric Miller, Lee E Kennedy, Ann |
author_sort | Ma, Xuan |
collection | PubMed |
description | Existing intracortical brain computer interfaces (iBCIs) transform neural activity into control signals capable of restoring movement to persons with paralysis. However, the accuracy of the ‘decoder’ at the heart of the iBCI typically degrades over time due to turnover of recorded neurons. To compensate, decoders can be recalibrated, but this requires the user to spend extra time and effort to provide the necessary data, then learn the new dynamics. As the recorded neurons change, one can think of the underlying movement intent signal being expressed in changing coordinates. If a mapping can be computed between the different coordinate systems, it may be possible to stabilize the original decoder’s mapping from brain to behavior without recalibration. We previously proposed a method based on Generalized Adversarial Networks (GANs), called ‘Adversarial Domain Adaptation Network’ (ADAN), which aligns the distributions of latent signals within underlying low-dimensional neural manifolds. However, we tested ADAN on only a very limited dataset. Here we propose a method based on Cycle-Consistent Adversarial Networks (Cycle-GAN), which aligns the distributions of the full-dimensional neural recordings. We tested both Cycle-GAN and ADAN on data from multiple monkeys and behaviors and compared them to a third, quite different method based on Procrustes alignment of axes provided by Factor Analysis. All three methods are unsupervised and require little data, making them practical in real life. Overall, Cycle-GAN had the best performance and was easier to train and more robust than ADAN, making it ideal for stabilizing iBCI systems over time. |
format | Online Article Text |
id | pubmed-10446822 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | eLife Sciences Publications, Ltd |
record_format | MEDLINE/PubMed |
spelling | pubmed-104468222023-08-24 Using adversarial networks to extend brain computer interface decoding accuracy over time Ma, Xuan Rizzoglio, Fabio Bodkin, Kevin L Perreault, Eric Miller, Lee E Kennedy, Ann eLife Neuroscience Existing intracortical brain computer interfaces (iBCIs) transform neural activity into control signals capable of restoring movement to persons with paralysis. However, the accuracy of the ‘decoder’ at the heart of the iBCI typically degrades over time due to turnover of recorded neurons. To compensate, decoders can be recalibrated, but this requires the user to spend extra time and effort to provide the necessary data, then learn the new dynamics. As the recorded neurons change, one can think of the underlying movement intent signal being expressed in changing coordinates. If a mapping can be computed between the different coordinate systems, it may be possible to stabilize the original decoder’s mapping from brain to behavior without recalibration. We previously proposed a method based on Generalized Adversarial Networks (GANs), called ‘Adversarial Domain Adaptation Network’ (ADAN), which aligns the distributions of latent signals within underlying low-dimensional neural manifolds. However, we tested ADAN on only a very limited dataset. Here we propose a method based on Cycle-Consistent Adversarial Networks (Cycle-GAN), which aligns the distributions of the full-dimensional neural recordings. We tested both Cycle-GAN and ADAN on data from multiple monkeys and behaviors and compared them to a third, quite different method based on Procrustes alignment of axes provided by Factor Analysis. All three methods are unsupervised and require little data, making them practical in real life. Overall, Cycle-GAN had the best performance and was easier to train and more robust than ADAN, making it ideal for stabilizing iBCI systems over time. eLife Sciences Publications, Ltd 2023-08-23 /pmc/articles/PMC10446822/ /pubmed/37610305 http://dx.doi.org/10.7554/eLife.84296 Text en © 2023, Ma, Rizzoglio et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited. |
spellingShingle | Neuroscience Ma, Xuan Rizzoglio, Fabio Bodkin, Kevin L Perreault, Eric Miller, Lee E Kennedy, Ann Using adversarial networks to extend brain computer interface decoding accuracy over time |
title | Using adversarial networks to extend brain computer interface decoding accuracy over time |
title_full | Using adversarial networks to extend brain computer interface decoding accuracy over time |
title_fullStr | Using adversarial networks to extend brain computer interface decoding accuracy over time |
title_full_unstemmed | Using adversarial networks to extend brain computer interface decoding accuracy over time |
title_short | Using adversarial networks to extend brain computer interface decoding accuracy over time |
title_sort | using adversarial networks to extend brain computer interface decoding accuracy over time |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10446822/ https://www.ncbi.nlm.nih.gov/pubmed/37610305 http://dx.doi.org/10.7554/eLife.84296 |
work_keys_str_mv | AT maxuan usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime AT rizzogliofabio usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime AT bodkinkevinl usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime AT perreaulteric usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime AT millerleee usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime AT kennedyann usingadversarialnetworkstoextendbraincomputerinterfacedecodingaccuracyovertime |