MIT AI Hardware Program

3D Integration of AI Hardware with Direct Analog Input from Sensor Arrays

Jeehwan Kim

This research group works on AI hardware based on memristor neural networks with emphasis on ultra-low power operation for inference and online training and 3D integration of AI hardware and Si electronics.

Principal Investigator: Jeehwan Kim

 

Jeehwan Kim’s group at MIT works on AI hardware based on memristor neural networks. The group’s focus is on ultralow power operation of artificial synapse arrays with robust analog computing and ultralow LRS. The group is equipped with large-scale arrays measurement system for inference and online training. More recently his group expanded their research for AI-driven non-Von Neuman heterogeneous integration systems and they have successfully implemented 3D integration of AI hardware with direct analog input from sensor arrays.

Explore

Privacy Preference Center

Privacy Preferences