Brain Co-processors: Using AI to Restore and Augment Brain Function

Rao, Rajesh P. N.

doi:10.1007/978-981-16-5540-1_32

Cited by 2 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a simulated model of cortical circuits in the primate brain that are involved in grasping behaviors, we demonstrated a training method based on deep learning for a closed-loop neural stimulator called a 'neural co-processor' [15,16]. We created a learning paradigm which allowed the co-processor to adapt to the distributed neural activity in the simulated brain, as well as to the non-stationarity of the neural activity and the sensors, key properties which are likely necessary for future in vivo applications.…”

Section: Discussionmentioning

confidence: 99%

“…Motivated by these advances, we investigate here a flexible framework for combining encoding and decoding using 'neural co-processors' [15], a type of brain co-processor [16]. Neural co-processors leverage artificial neural networks (ANNs) and deep learning to compute optimal closed-loop stimulation patterns.…”

Section: Introductionmentioning

confidence: 99%

“…from cameras or light detection and ranging sensors, in order to restore perception (e.g. cortical visual prosthesis) or incorporate feedback for real-time prosthetic control (see [16] for details).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural co-processors for restoring brain function: results from a cortical model of grasping

Bryan

Jiang

2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective: A major challenge in designing closed-loop brain-computer interfaces (BCIs) is finding optimal stimulation patterns as a function of ongoing neural activity for different subjects and objectives. Traditional approaches, such as those currently used for deep brain stimulation (DBS), have largely followed a manual trial-and-error strategy to search for effective open-loop stimulation parameters, a strategy that is inefficient and does not generalize to closed-loop activity-dependent stimulation. Approach: To achieve goal-directed closed-loop neurostimulation, we propose the use of neural co-processors, devices which use artificial neural networks (ANNs) and deep learning to learn optimal closed-loop stimulation policies to shape neural activity and bridge injured neural circuits for targeted repair and restoration of function. The co-processor adapts the stimulation policy as the biological circuit itself adapts to the stimulation, achieving a form of brain-device co-adaptation. Here we use simulations to lay the groundwork for future in vivo tests of neural co-processors. We leverage a previously published cortical model of grasping, to which we applied various forms of simulated lesions. We used our simulations to develop the critical learning algorithms and study adaptations to non-stationarity. Main results: Our simulations show the ability of a neural co-processor to learn a stimulation policy using a supervised learning approach, and to adapt that policy as the underlying brain and sensors change. Our co-processor successfully co-adapted with the simulated brain to accomplish the reach-and-grasp task after a variety of lesions were applied. Significance: Our results provide the first proof-of-concept demonstration, using computer simulations, of a neural co-processor for adaptive activity-dependent closed-loop neurostimulation for optimizing a rehabilitation goal after injury. While a significant gap remains between simulations and in vivo applications, our results provide insights on how such co-processors may eventually be developed for learning complex adaptive stimulation policies for a variety of neural rehabilitation and neuroprosthetic applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%