KAIST Develops AI Chip That Recognizes Changes in Motion over Time (IMAGE)
Caption
Figure 1. Monolithic 3D-integrated multi-timescale reservoir architecture based on solid ion-gated transistors
Thin-film carbon nanotube (CNT) ion-gated transistors were fabricated using an ionogel, in which ions are embedded in a polymer matrix to form a solid. By varying the ionic content, the transistors were designed to show different ionic dynamics and response times. Devices with different time characteristics were then stacked vertically to create a 3D reservoir architecture that can process information on multiple timescales within a single hardware platform.
Credit
KAIST
Usage Restrictions
No
License
Licensed content