•In recent years, artificial intelligence has achieved unprecedented accuracies in large-scale recognition and classification tasks by utilizing supercomputing resources optimized for artificial neural networks. While several application-specific integrated circuit (ASIC) solutions utilizing CMOS have been previously proposed, limitations still exist on communication bottlenecks, energy consumption, and online learning capabilities.

 

To address all issues in AI hardware, the community is moving towards utilizing memristors as artificial synapses because they can offer fast parallel neuromorphic computing at extremely small device footprint with low power consumption. The goal of this project is to develop large-scale neuromorphic systems for artificial intelligence (AI) hardware using artificial synapses (mainly memristors) developed by the team.

 

Our team focuses on the integration of intelligent systems from input sensors to computing units. By utilizing emerging device-based computing systems, our team is working on demonstration of fully integrated systems from artificial neurons to artificial synapses. Furthermore, we are also working on emerging device-based domain-specific architectures (DSA) utilizing our device, by designing the framework using hardware such as digital and analog peripheral circuits and controllers, and software development for artificial intelligence.