IEEE Brain: Optimizing Control and Learning in Neural Interfaces

Direct interfaces with the brain provide exciting new ways to restore and repair neurological function. For instance, motor Brain-Machine Interfaces (BMIs) can bypass a paralyzed person's injury by repurposing intact portions of their brain to control movements. Recent work shows that BMIs do not simply "decode" subjects' intentions - they create new systems subjects learn to control. To improve BMI performance and usability, we must therefore understand how to optimize learning and control in these systems. I will present a survey of recent work and new directions exploring how the design of BMI systems influence BMI performance. I'll touch on the importance of control loop design, brain-decoder interactions and multi-learner approaches, and network-informed neural signal selection. These examples highlight the role of learning and closed-loop in BMIs, and demonstrate the promise of engineering approaches based on optimizing learning and control along with information "decoding."
  • IEEE MemberUS $10.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $10.00
  • Non-IEEE MemberUS $20.00
Purchase

Videos in this product

IEEE Brain: Optimizing Control and Learning in Neural Interfaces

01:06:03
2 views
Direct interfaces with the brain provide exciting new ways to restore and repair neurological function. For instance, motor Brain-Machine Interfaces (BMIs) can bypass a paralyzed person's injury by repurposing intact portions of their brain to control movements. Recent work shows that BMIs do not simply "decode" subjects' intentions - they create new systems subjects learn to control. To improve BMI performance and usability, we must therefore understand how to optimize learning and control in these systems. I will present a survey of recent work and new directions exploring how the design of BMI systems influence BMI performance. I'll touch on the importance of control loop design, brain-decoder interactions and multi-learner approaches, and network-informed neural signal selection. These examples highlight the role of learning and closed-loop in BMIs, and demonstrate the promise of engineering approaches based on optimizing learning and control along with information "decoding."