[23a-12J-1~12] 13.5 Semiconductor devices/ Interconnect/ Integration technologies

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)

[23a-12J-3] Trial for Prediction of Cryo-CMOS Characteristics Utilizing Transfer-Learning

〇Takumi Inaba¹, Yusuke Chiashi¹, Minoru Ogura¹, Hidehiro Asai¹, Hiroshi Fuketa¹, Hiroshi Oka¹, Shota Iizuka¹, Kimihiko Kato¹, Shunsuke Shitakata¹, Takahiro Mori¹ (1.AIST)

Keywords:

Neural Network,Cryo-CMOS,Quantum Computer

Cryo-CMOS technology for controlling qubits is attracting much attention. Many cryogenic characteristics of MOSFETs need to be obtained to design Cryo-CMOS circuits. However, cryogenic characterization is laborous and time consuming tasks. In order to ammend this situation, we will introduce a method to predict cryogenic characteristics from small number of experimental data by using transfer learning of neural networks.