Theoretical constructs from biophysics have profoundly impacted signal processing and engineering from McCulloch-Pitts' theory of mind seeding modern computer design (von Neumann) to the hierarchical neural network approach underlying recent breakthroughs in deep learning. This history will be discussed as the backdrop for a new retina-inspired paradigm for digital sensory encoding, which began at the Redwood Center for Theoretical Neuroscience (founded by Jeff Hawkins), UC Berkeley, and is now fueling initial applications in signal processing. Consequences for source/channel coding, learning in AI, brain-machine interfaces, and experimental neuroscience will also be explored.
Back to Workshop III: Naturalistic Approaches to Artificial Intelligence
Copyright. All Rights Reserved.