A Business / Market Opportunity Assessment for Hardware Concepts & Device Designs for Brain-Machine Interfacing

点击翻译按钮获取中文摘要

Through advances in brain sensing technology and in neuroscience we are witnessing the emergence of applications that process brain activity data with applications in drug discovery (e.g., decyphering what an animal feels after administering a potential drug) and therapeutics (e.g., recovery or treatment, articles outlining recent developments have even made it into main stream news "Tapping into the Brain to Help a Paralyzed Man to Speak" NY Times and "Brain Implant Gives Blind Woman Artificial Vision in Scientific First" ScienceAlert). In most cases, the data sensed from the brain are converted to digital signals and processed in the digital domain. Unfortunately the amount of computation and memory bandwidth needed for many of these emerging applications far exceed the capability of modern computing systems. However, through specialization we are showing that it is possible to enable such applications to work in real time and in a form factor that makes truly autonomous operation possible. We are seeking the support needed to perform a market assessment for the potential customers and market for our brain-machine computing system. There are numerous applications such as prosthetics, brain function repair/augmentation, and pharmaceutical drug discovery. However, for such applications to become practical, optimized algorithms and dedicated, autonomous wearable processing hardware are essential to analyze and act upon the data in real-time. While these applications will eventually gain approval for use in humans, there is large potential for more immediate use in animal models in a lab setting. Our group, in close collaboration with fully-committed neuroscientists, has been developing hardwareconcepts and designs for digital processing hardware for brain-machine interfacing (BMI) that make suchapplications practical for the first time. Our group is uniquely positioned to deliver the innovations necessary given our decades long expertise in designing high-performance and energy-efficient digital hardware engines, and our extensive experience in designing machine learning hardware.