Neural interface systems with on-device computing: machine learning and neuromorphic architectures

[Display omitted] •Neural interfaces continue to improve in channel count and form factor.•Low-power machine learning and neuromorphic processors can be integrated onto neural devices.•Neural system-on-chips with on-device computing enable real-time closed-loop therapies.•On-chip machine learning eliminates power-hungry data movement to external devices. Development of neural interface and brain-machine interface (BMI) systems enables the treatment of neurological disorders including cognitive, sensory, and motor dysfunctions. While neural interfaces have steadily decreased in form factor, recent developments target pervasive implantables. Along with advances in electrodes, neural recording, and neurostimulation circuits, integration of disease biomarkers and machine learning algorithms enables real-time and on-site processing of neural activity with no need for power-demanding telemetry. This recent trend on combining artificial intelligence and machine learning with modern neural interfaces will lead to a new generation of low-power, smart, and miniaturized therapeutic devices for a wide range of neurological and psychiatric disorders. This paper reviews the recent development of the ‘on-chip’ machine learning and neuromorphic architectures, which is one of the key puzzles in devising next-generation clinically viable neural interface systems.