Stabilization of a brain–computer interface via the alignment of low-dimensional spaces of neural activity

Degenhart, Alan D.; Bishop, William E.; Oby, Emily R.; Tyler-Kabara, Elizabeth C.; Chase, Steven M.; Batista, Aaron P.; Yu, Byron M.

doi:10.1038/s41551-020-0542-9

Cited by 144 publications

(175 citation statements)

References 74 publications

(113 reference statements)

Supporting

Mentioning

152

Contrasting

Order By: Relevance

“…Theoretical work has proposed that a consistent readout of a representation can be achieved if drift in neural activity patterns occurs in dimensions of population activity that are orthogonal to coding dimensions - in a ‘null coding space’ ( Rokni et al, 2007 ; Druckmann and Chklovskii, 2012 ; Ajemian et al, 2013 ; Singh et al, 2019 ). This can be facilitated by neural representations that consist of low-dimensional dynamics distributed over many neurons ( Montijn et al, 2016 ; Gallego et al, 2018 ; Hennig et al, 2018 ; Degenhart et al, 2020 ). Redundancy could therefore permit substantial reconfiguration of tuning in single cells without disrupting neural codes ( Druckmann and Chklovskii, 2012 ; Huber et al, 2012 ; Kaufman et al, 2014 ; Ni et al, 2018 ; Kappel et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Stable task information from an unstable neural population

Rule

Loback

Raman

et al. 2020

eLife

View full text Add to dashboard Cite

Over days and weeks, neural activity representing an animal's position and movement in sensorimotor cortex has been found to continually reconfigure or 'drift' during repeated trials of learned tasks, with no obvious change in behavior. This challenges classical theories which assume stable engrams underlie stable behavior. However, it is not known whether this drift occurs systematically, allowing downstream circuits to extract consistent information. Analyzing long-term calcium imaging recordings from posterior parietal cortex in mice (Mus musculus), we show that drift is systematically constrained far above chance, facilitating a linear weighted readout of behavioural variables. However, a significant component of drift continually degrades a fixed readout, implying that drift is not confined to a null coding space. We calculate the amount of plasticity required to compensate drift independently of any learning rule, and find that this is within physiologically achievable bounds. We demonstrate that a simple, biologically plausible local learning rule can achieve these bounds, accurately decoding behavior over many days.

show abstract

Section: Introductionmentioning

confidence: 99%

Stable task information from an unstable neural population

Rule

Loback

Raman

et al. 2020

eLife

View full text Add to dashboard Cite

show abstract

“…Threshold crossings are vulnerable to amplitude shifts in neural recordings, while features based on spectral power may be more robust (Zhang et al, 2018 ; Allahgholizadeh Haghi et al, 2019 ). BMIs may also leverage neural manifolds (Gallego et al, 2017 , 2020 ; Degenhart et al, 2020 ), low dimensional projections that capture much of the variance in neural population activity, to combat transient disruptions. Degenhart et al stabilize neural activity by aligning manifolds across time and show that this method can counteract recording disruptions including changes in baseline firing rate and neural tuning, as well as loss of recorded units (Degenhart et al, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Classifying Intracortical Brain-Machine Interface Signal Disruptions Based on System Performance and Applicable Compensatory Strategies: A Review

et al. 2020

View full text Add to dashboard Cite

Brain-machine interfaces (BMIs) record and translate neural activity into a control signal for assistive or other devices. Intracortical microelectrode arrays (MEAs) enable high degree-of-freedom BMI control for complex tasks by providing fine-resolution neural recording. However, chronically implanted MEAs are subject to a dynamic in vivo environment where transient or systematic disruptions can interfere with neural recording and degrade BMI performance. Typically, neural implant failure modes have been categorized as biological, material, or mechanical. While this categorization provides insight into a disruption's causal etiology, it is less helpful for understanding degree of impact on BMI function or possible strategies for compensation. Therefore, we propose a complementary classification framework for intracortical recording disruptions that is based on duration of impact on BMI performance and requirement for and responsiveness to interventions: (1) Transient disruptions interfere with recordings on the time scale of minutes to hours and can resolve spontaneously; (2) Reversible disruptions cause persistent interference in recordings but the root cause can be remedied by an appropriate intervention; (3) Irreversible compensable disruptions cause persistent or progressive decline in signal quality, but their effects on BMI performance can be mitigated algorithmically; and (4) Irreversible non-compensable disruptions cause permanent signal loss that is not amenable to remediation or compensation. This conceptualization of intracortical BMI disruption types is useful for highlighting specific areas for potential hardware improvements and also identifying opportunities for algorithmic interventions. We review recording disruptions that have been reported for MEAs and demonstrate how biological, material, and mechanical mechanisms of disruption can be further categorized according to their impact on signal characteristics. Then we discuss potential compensatory protocols for each of the proposed disruption classes. Specifically, transient disruptions may be minimized by using robust neural decoder features, data augmentation methods, adaptive machine learning models, and specialized signal referencing techniques. Statistical Process Control methods can identify reparable disruptions for rapid intervention. In-vivo diagnostics such as impedance spectroscopy can inform neural feature selection and decoding models to compensate for irreversible disruptions. Additional compensatory strategies for irreversible disruptions include information salvage techniques, data augmentation during decoder training, and adaptive decoding methods to down-weight damaged channels.

show abstract

“…The new data were combined with all previous days' data into one large dataset while training. To account for differences in neural activity across days 6,48 , we separately transformed each days' neural activity with a linear transformation that was simultaneously optimized with the other RNN parameters. Including multiple days of data, and fitting separate input layers for each day, substantially improved performance (SFig.…”

Section: Recurrent Neural Network Decodermentioning

confidence: 99%

High-performance brain-to-text communication via imagined handwriting

Willett

Avansino

Hochberg

et al. 2020

Preprint

View full text Add to dashboard Cite

SummaryBrain-computer interfaces (BCIs) can restore communication to people who have lost the ability to move or speak. To date, a major focus of BCI research has been on restoring gross motor skills, such as reaching and grasping1–5 or point-and-click typing with a 2D computer cursor6,7. However, rapid sequences of highly dexterous behaviors, such as handwriting or touch typing, might enable faster communication rates. Here, we demonstrate an intracortical BCI that can decode imagined handwriting movements from neural activity in motor cortex and translate it to text in real-time, using a novel recurrent neural network decoding approach. With this BCI, our study participant (whose hand was paralyzed) achieved typing speeds that exceed those of any other BCI yet reported: 90 characters per minute at >99% accuracy with a general-purpose autocorrect. These speeds are comparable to able-bodied smartphone typing speeds in our participant’s age group (115 characters per minute)8 and significantly close the gap between BCI-enabled typing and able-bodied typing rates. Finally, new theoretical considerations explain why temporally complex movements, such as handwriting, may be fundamentally easier to decode than point-to-point movements. Our results open a new approach for BCIs and demonstrate the feasibility of accurately decoding rapid, dexterous movements years after paralysis.

show abstract

Stabilization of a brain–computer interface via the alignment of low-dimensional spaces of neural activity

Cited by 144 publications

References 74 publications

Stable task information from an unstable neural population

Stable task information from an unstable neural population

Classifying Intracortical Brain-Machine Interface Signal Disruptions Based on System Performance and Applicable Compensatory Strategies: A Review

High-performance brain-to-text communication via imagined handwriting

Contact Info

Product

Resources

About