Researchers develop a redox-based transistor as a reservoir system for neuromorphic computing

Physical systems known as "reservoirs" are designed to emulate neural networks and meet the need for improved computational efficiency and speed. Overcoming the previous issues with compatibility, performance, and integration of such reservoir systems, researchers from Japan have recently developed an ion-gating transistor with improved reservoir states and short-term memory capabilities based on redox reactions. This development opens us the possibility of utilizing redox-based ionic devices for high-performance neuromorphic computing.

computational computing efficiency electronics & semiconductors integration japan networks neural networks neuromorphic neuromorphic computing performance researchers speed systems