Monolithic 3D Memristor-TFT Stack For Programmable Neuromorphic Computing (SNU, Yonsei)

AI introduction

A research team from Seoul National University and Yonsei University published a paper in Nature Communications proposing a monolithically 3D-integrated memristor-thin-film transistor (TFT) reservoir computing kernel. The structure vertically integrates Ru/HfO2/TiN memristors with In2O3 channel TFTs, using the TFTs to electrically modulate memristive conductance dynamics to achieve programmable temporal dynamics over wide timescales, overcoming the fixed dynamics or narrow tuning ranges of most hardware reservoirs.

Article · English

Researchers at Seoul National University and Yonsei University published a technical paper titled “Monolithic three-dimensionally integrated memristor-thin-film transistor for electrically programmable multimode reservoir computing.”

Abstract Excerpt:

“Reservoir computing offers an efficient framework for processing temporal information, but most hardware reservoirs exhibit fixed or narrowly tunable dynamics determined by intrinsic material relaxation time. A monolithically integrated memristor-thin-film transistor reservoir kernel of this study enables electrically programmable temporal dynamics across a wide timescale. By vertically and monolithically integrating Ru/HfO₂/TiN memristors with In₂O₃ channel thin-film transistors (TFTs), the memristive conductance dynamics are modulated by the TFTs.”

Find the technical paper here. October 2026.

Shim, Sung Keun, Wonho Choi, Sunwoo Cheong, Dong Hoon Shin, Jonghoon Shin, Janguk Han, Jiseong Im, et al. “Monolithic three-dimensionally integrated memristor-thin-film transistor for electrically programmable multimode reservoir computing.” Nature Communications (2026). https://doi.org/10.1038/s41467-026-78364-5

The post Monolithic 3D Memristor-TFT Stack For Programmable Neuromorphic Computing (SNU, Yonsei) appeared first on Semiconductor Engineering.