Artificial Intelligence (AI) solutions are taking the lead in pioneering research to develop the next-generation technologies. The next stage of AI systems promises to have improved robustness and reliability; enhanced security; reduced power, data, and performance inefficiencies; and enable common sense reasoning. AI applications include, but are not limited to, smart healthcare systems, self-driving cars, robotics, etc. Conventional CMOS technology, which has provided cheaper, faster, and lower power electronics system over the past 40-years, is facing big challenges. In addition, von Neumann architecture does not match the characteristics of machine learning algorithms, hence researchers are looking into novel technology and hardware architectures for accelerating such algorithms. In this project, DeepMem, an efficient intelligent Memristor-based hardware system, is introduced. Memristor technology enables efficient in-memory computations with low power and high density. Co-optimization of machine learning algorithms, as well as Memristor-based in-memory computing for IoT devices, is the main aim of this project.
