Chung, Chia CheChia CheChungHuang, Bo WeiBo WeiHuangLin, Hsin ChengHsin ChengLinChou, TaoTaoChouTsen, Chia JungChia JungTsenCHEE-WEE LIU2023-04-202023-04-202022-08-0107413106https://scholars.lib.ntu.edu.tw/handle/123456789/630384A series of multi-correlated recurrent neural networks is used to predict the relative temperature of inverter chains folded in 3 rows. The circuit hotspot temperature is predicted by a fully connected neural network. The correlated recurrent neural networks trained by the SPICE data within 17 stages can predict T up to 37 stages (2.2× SPICE complexity) with the error as low as 0.9 °C, outperforming the previous fully connected neural network (1.9× SPICE, 3 °C error) and non-correlated recurrent neural network (2.2× SPICE, 3 °C error) by considering the thermal coupling between rows. The precise prediction of temperature profiles and hotspot positions indicate that the thermal physics is learned by correlated recurrent neural networks. Therefore, an 82-stage folded inverter chain can be predicted and optimized confidently by neural networks, while SPICE can only simulate a 37-stage chain due to the high computational cost. A 100-stage chain is also predicted.chain circuit | FinFETs | neural network | self-heatingjournal article10.1109/LED.2022.31833822-s2.0-85132774626WOS:000831160000010https://api.elsevier.com/content/abstract/scopus_id/85132774626