Abstract: In the era of ​‘big data’ and ​‘Internet of Things’, the traditional computing architecture based on CMOS hardware has become increasingly inefficient to support Artificial Intelligence (AI) and Machine Learning (ML), which necessitates some emerging technologies, such as memristive devices, including memristors and memcapacitors. These devices are beyond the traditional static RRAMs (Resistive Random Access Memory) in that they are dynamical and analog, which makes them well-suited to enable efficient computing applications. I will first introduce the cutting-edge development in these devices, and then discuss how to use such device to accelerate ML learning and emulate neuromorphic systems.