Device Codesign using Reinforcement Learning and Evolutionary Optimization

Catherine Schuman, Suma G Cardwell, Karan P. Patel, J. Darby Smith, Jared Arzate, Andrew Maicke, Samuel Liu, Jaesuk Kwon, Jean Anne Incorvia

Keywords: emerging devices, AI-guided Codesign, Reinforcement learning, evolutioanry optiomization, MTJ

TL;DR: AI-Guided Codesign for Device Discovery and Codesign

Abstract: Device discovery and circuit modeling for emerging devices, such as magnetic tunnel junctions, require detailed and time-consuming device and circuit simulations. In this work, we propose using AI-guided techniques such as reinforcement learning and evolutionary optimization to accelerate device discovery, creativity of solutions, and automate optimization to design true random number generators for a given distribution. We present preliminary results designing true random number generators using magnetic tunnel junctions optimized for performance.

Submission Number: 25