Brainmorphic computing: Paradigm and hardware

Abstract

A brainmorphic computing (BMC) paradigm, a new framework for brain-like computing, is necessary for realizing a highly efficient and high-performance brain-specific information processing that emerged evolutionarily in the brain. The BMC paradigm should consider the tight relationship between complex structure and computation, high-dimensional integrated dynamics, embodiment, and computation through biophysical phenomena. Furthermore, a dedicated hardware, i.e., brainmorphic computing hardware (BMC-HW), is mandatory for reproducing the BMC paradigm, through which highly efficient, high-performance, and brain-like computation can be realized as a practical engineering system. It is natural and essential to employ continuous-value and continuous-time physical phenomena in BMC-HW like the brain. This study reviews the BMC paradigm and BMC-HW framework with some implementation examples, which we have developed. In addition, extensions of the BMC paradigm and BMC-HW framework to a complex spatiotemporal information processing through event-driven, continuous-value, continuous-time, asynchronous spiking neural networks are discussed, which is closer to the way the brain processes information. Furthermore, novel device and circuit technologies to realize the extended BMC paradigm are introduced.