Neuroprosthetic Decoder Training as Imitation Learning
- PMID: 27191387
- PMCID: PMC4871564
- DOI: 10.1371/journal.pcbi.1004948
Neuroprosthetic Decoder Training as Imitation Learning
Abstract
Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user's intended movement. Here we show that training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector.
Conflict of interest statement
The authors have declared that no competing interests exist.
Figures
![Fig 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g001.gif)
![Fig 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g002.gif)
![Fig 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g003.gif)
![Fig 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g004.gif)
![Fig 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g005.gif)
![Fig 6](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g006.gif)
![Fig 7](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g007.gif)
![Fig 8](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/4871564/bin/pcbi.1004948.g008.gif)
Similar articles
-
Encoder-decoder optimization for brain-computer interfaces.PLoS Comput Biol. 2015 Jun 1;11(6):e1004288. doi: 10.1371/journal.pcbi.1004288. eCollection 2015 Jun. PLoS Comput Biol. 2015. PMID: 26029919 Free PMC article.
-
Unsupervised adaptation of an ECoG based brain-computer interface using neural correlates of task performance.Sci Rep. 2022 Dec 9;12(1):21316. doi: 10.1038/s41598-022-25049-w. Sci Rep. 2022. PMID: 36494390 Free PMC article.
-
Robust Brain-Machine Interface Design Using Optimal Feedback Control Modeling and Adaptive Point Process Filtering.PLoS Comput Biol. 2016 Apr 1;12(4):e1004730. doi: 10.1371/journal.pcbi.1004730. eCollection 2016 Apr. PLoS Comput Biol. 2016. PMID: 27035820 Free PMC article.
-
Adaptive neuron-to-EMG decoder training for FES neuroprostheses.J Neural Eng. 2016 Aug;13(4):046009. doi: 10.1088/1741-2560/13/4/046009. Epub 2016 Jun 1. J Neural Eng. 2016. PMID: 27247280 Free PMC article.
-
Applications of brain-computer interfaces to the control of robotic and prosthetic arms.Handb Clin Neurol. 2020;168:87-99. doi: 10.1016/B978-0-444-63934-9.00008-1. Handb Clin Neurol. 2020. PMID: 32164870 Review.
Cited by
-
Workshops of the Sixth International Brain-Computer Interface Meeting: brain-computer interfaces past, present, and future.Brain Comput Interfaces (Abingdon). 2017;4(1-2):3-36. doi: 10.1080/2326263X.2016.1275488. Epub 2017 Jan 30. Brain Comput Interfaces (Abingdon). 2017. PMID: 29152523 Free PMC article.
References
-
- Serruya MD, Hatsopoulos NG, Paninski L, Fellows MR, Donoghue JP. Brain-machine interface: Instant neural control of a movement signal. Nature. 2002;416(6877):141–142. - PubMed
Publication types
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources