Neuromorphic Control: Designing Multiscale Mixed-Feedback Systems

Neuromorphic electronic engineering takes inspiration from the biological organization of nervous systems to rethink the technology of computing, sensing, and actuating (see Summary). It started three decades ago with the realization by Carver Mead, a pioneer of very large-scale integration (VLSI) technology, that the operation of a conventional transistor in the analog regime closely resembles the biophysical operation of a neuron [1]. Mead envisioned a novel generation of electronic circuits that would operate far more efficiently than conventional VLSI technology and would allow for a new generation of biologically inspired sensing devices. Three decades later, active vision has become a technological reality [2], [3], and neuromorphic computing has emerged as a promising avenue to reduce the energy requirements of digital computers [4]-[7]. These two applications could just be the tip of the iceberg. Neuromorphic circuit architectures call for new computing, signal processing, and control paradigms.

Automated summary

Neuromorphic electronic engineering draws inspiration from the biological organization of nervous systems to rethink computing, sensing, and actuating technology. Three decades later, active vision has become a technological reality, and neuromorphic computing has emerged promisingly to reduce the energy requirements of digital computers.