Search for: All records

A convenient method based on deep neural networks and an evolutionary algorithm is proposed for the inverse design of FinFET SRAM cells. Inverse design helps designers who have less device physics knowledge obtain cell configurations that provide the desired performance metrics under selected wearout conditions, such as a set specific stress time and use scenario that creates a specific activity level (duty cycle and transition rate). The cell configurations being considered consists of various process parameters, such as gate length and fin height, in the presence of variations due to process and wearout. The front-end mechanisms related to wearout include negative bias temperature instability (NBTI), hot carrier injection (HCI), and random telegraph noise (RTN). The process of inverse design is achieved quickly and at good accuracy. 

Abstract Machine learning, as a study of algorithms that automate prediction and decision‐making based on complex data, has become one of the most effective tools in the study of artificial intelligence. In recent years, scientific communities have been gradually merging data‐driven approaches with research, enabling dramatic progress in revealing underlying mechanisms, predicting essential properties, and discovering unconventional phenomena. It is becoming an indispensable tool in the fields of, for instance, quantum physics, organic chemistry, and medical imaging. Very recently, machine learning has been adopted in the research of photonics and optics as an alternative approach to address the inverse design problem. In this report, the fast advances of machine‐learning‐enabled photonic design strategies in the past few years are summarized. In particular, deep learning methods, a subset of machine learning algorithms, dealing with intractable high degrees‐of‐freedom structure design are focused upon.