Brain-machine interface control via reinforcement learning

Jack DiGiovanna, Babak Mahmoudi, Jeremiah Mitzelfelt, Justin C. Sanchez, Jose C. Principe

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

We investigate the capabilities of reinforcement learning (RL) to create a brain-machine interface (BMI) that uses Q(λ) learning to find the functional mapping between neural activity and intended behavior. This paradigm shift is intended to address the issue of paralyzed and amputee patients whom are physically unable to move, which is necessary to train traditional supervised learning BMIs. We created a RLBMI architecture incorporating a rat behavioral paradigm for prosthetic arm control. The performance results show 'proof of concept' that RLBMI can learn the temporal structure of neural signals to control a prosthetic arm.

Original languageEnglish
Title of host publicationProceedings of the 3rd International IEEE EMBS Conference on Neural Engineering
Pages530-533
Number of pages4
DOIs
StatePublished - Sep 25 2007
Externally publishedYes
Event3rd International IEEE EMBS Conference on Neural Engineering - Kohala Coast, HI, United States
Duration: May 2 2007 → May 5 2007

Other

Other3rd International IEEE EMBS Conference on Neural Engineering
CountryUnited States
CityKohala Coast, HI
Period5/2/07 → 5/5/07

Fingerprint

Brain-Computer Interfaces
Reinforcement learning
Prosthetics
Brain
Learning
Supervised learning
Rats
Amputees
Reinforcement (Psychology)

ASJC Scopus subject areas

  • Biotechnology
  • Bioengineering
  • Neuroscience (miscellaneous)

Cite this

DiGiovanna, J., Mahmoudi, B., Mitzelfelt, J., Sanchez, J. C., & Principe, J. C. (2007). Brain-machine interface control via reinforcement learning. In Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering (pp. 530-533). [4227331] https://doi.org/10.1109/CNE.2007.369726

Brain-machine interface control via reinforcement learning. / DiGiovanna, Jack; Mahmoudi, Babak; Mitzelfelt, Jeremiah; Sanchez, Justin C.; Principe, Jose C.

Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. p. 530-533 4227331.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

DiGiovanna, J, Mahmoudi, B, Mitzelfelt, J, Sanchez, JC & Principe, JC 2007, Brain-machine interface control via reinforcement learning. in Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering., 4227331, pp. 530-533, 3rd International IEEE EMBS Conference on Neural Engineering, Kohala Coast, HI, United States, 5/2/07. https://doi.org/10.1109/CNE.2007.369726
DiGiovanna J, Mahmoudi B, Mitzelfelt J, Sanchez JC, Principe JC. Brain-machine interface control via reinforcement learning. In Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. p. 530-533. 4227331 https://doi.org/10.1109/CNE.2007.369726
DiGiovanna, Jack ; Mahmoudi, Babak ; Mitzelfelt, Jeremiah ; Sanchez, Justin C. ; Principe, Jose C. / Brain-machine interface control via reinforcement learning. Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. pp. 530-533
@inproceedings{b9df03c0647f4773a301f1f4b073cd47,
title = "Brain-machine interface control via reinforcement learning",
abstract = "We investigate the capabilities of reinforcement learning (RL) to create a brain-machine interface (BMI) that uses Q(λ) learning to find the functional mapping between neural activity and intended behavior. This paradigm shift is intended to address the issue of paralyzed and amputee patients whom are physically unable to move, which is necessary to train traditional supervised learning BMIs. We created a RLBMI architecture incorporating a rat behavioral paradigm for prosthetic arm control. The performance results show 'proof of concept' that RLBMI can learn the temporal structure of neural signals to control a prosthetic arm.",
author = "Jack DiGiovanna and Babak Mahmoudi and Jeremiah Mitzelfelt and Sanchez, {Justin C.} and Principe, {Jose C.}",
year = "2007",
month = "9",
day = "25",
doi = "10.1109/CNE.2007.369726",
language = "English",
isbn = "1424407923",
pages = "530--533",
booktitle = "Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering",

}

TY - GEN

T1 - Brain-machine interface control via reinforcement learning

AU - DiGiovanna, Jack

AU - Mahmoudi, Babak

AU - Mitzelfelt, Jeremiah

AU - Sanchez, Justin C.

AU - Principe, Jose C.

PY - 2007/9/25

Y1 - 2007/9/25

N2 - We investigate the capabilities of reinforcement learning (RL) to create a brain-machine interface (BMI) that uses Q(λ) learning to find the functional mapping between neural activity and intended behavior. This paradigm shift is intended to address the issue of paralyzed and amputee patients whom are physically unable to move, which is necessary to train traditional supervised learning BMIs. We created a RLBMI architecture incorporating a rat behavioral paradigm for prosthetic arm control. The performance results show 'proof of concept' that RLBMI can learn the temporal structure of neural signals to control a prosthetic arm.

AB - We investigate the capabilities of reinforcement learning (RL) to create a brain-machine interface (BMI) that uses Q(λ) learning to find the functional mapping between neural activity and intended behavior. This paradigm shift is intended to address the issue of paralyzed and amputee patients whom are physically unable to move, which is necessary to train traditional supervised learning BMIs. We created a RLBMI architecture incorporating a rat behavioral paradigm for prosthetic arm control. The performance results show 'proof of concept' that RLBMI can learn the temporal structure of neural signals to control a prosthetic arm.

UR - http://www.scopus.com/inward/record.url?scp=34548751154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548751154&partnerID=8YFLogxK

U2 - 10.1109/CNE.2007.369726

DO - 10.1109/CNE.2007.369726

M3 - Conference contribution

SN - 1424407923

SN - 9781424407927

SP - 530

EP - 533

BT - Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

ER -

Access to Document