Brain-Inspired Computing: The Extraordinary Voyages in Known and Unknown Worlds
Human brain is the most sophisticated organ that nature ever builds. Building a machine that can function like a human brain, indubitably, is the ultimate dream of a computer architect. Although we have not yet fully understood the working mechanism of human brains, the part that we have learned in past seventy years already guided us to many remarkable successes in computing applications, e.g., artificial neural network and machine learning. The recently emerged research on “neuromorphic computing”, which stands for hardware acceleration of brain-inspired computing, has become one of the most active areas in computer engineering. The talk will start with a background introduction of neuromorphic computing, followed by examples of hardware acceleration schemes of learning and neural network algorithms and memristor-based computing engine. I will also share our prospects on the future technology challenges and advances of neuromorphic computing.