Memristive crossbar arrays perform multiply–accumulate operations by utilizing physical laws, boosting power efficiency and computing throughput. Based on ionic motion, memristive devices are also bio-realistic emulators for artificial neurons and synapses. In this talk, I will first introduce a computing memristor for analog in-memory computing. I will then showcase an AI accelerator made by integrating memristive crossbars with CMOS circuitry. Finally, I will discuss a diffusive memristor and its application in neuromorphic engineering.
This event is a joint Microsystems Technology Laboratories (MTL) and AI Hardware Program Seminar.
Speaker
Qiangfei Xia
Dr. Xia directs the Nanodevices and Integrated Systems Lab (http://nano.ecs.umass.edu) at UMass Amherst. His research interests include beyond-CMOS devices, integrated systems, and enabling technologies, with applications in machine intelligence, reconfigurable RF systems, and hardware security. He is a ‘highly cited researcher’ (Clarivate) and an IEEE Fellow
Explore
Photonic Processor Could Enable Ultrafast AI Computations with Extreme Energy Efficiency
Adam Zewe | MIT News
This new device uses light to perform the key operations of a deep neural network on a chip, opening the door to high-speed processors that can learn in real-time.
AI Method Radically Speeds Predictions of Materials’ Thermal Properties
Adam Zewe | MIT News
The approach could help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.
A New Way to Let AI Chatbots Converse All Day without Crashing
Adam Zewe | MIT News
Researchers developed a simple yet effective solution for a puzzling problem that can worsen the performance of large language models such as ChatGPT.