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.

MIT and Ericsson Enter Collaboration Agreements to Research the Next Generation of Mobile Networks

Elizabeth A. Thomson | Materials Research Laboratory

A collaboration between MIT and Ericsson will explore new materials for computer chips that mimic the structure of the human brain as well as how to make some electronic systems truly autonomous by removing the need for charging.

close up of computer chip in shades of green and brown

Need to Fit Billions of Transistors on a Chip? Let AI Do It

Will Knight | Wired Magazine

Artificial Intelligence is now helping to design computer chips—including the very ones needed to run the most powerful AI code.

Crossing the Hardware-Software Divide for Faster AI

Thursday, April 29, 2021 | 12pm - 1pm ET

Panel Discussion: Vivienne Sze, Song Han, Aude Oliva

Vivienne Sze in her lab (photo credit: Lili Paquette)

Q&A: Vivienne Sze on Crossing the Hardware-Software Divide for Efficient Artificial Intelligence

Kim Martineau | MIT Quest for Intelligence

Vivienne Sze part of the pioneering team that won an Engineering Emmy Award for co-designing energy-efficient circuits with energy-efficient algorithms and developing the video compression standards still in use today, has set her sights on a new milestone: bringing artificial intelligence applications to smartphones and tiny robots.

computer chips credit: getty images

AI Algorithms Are Slimming Down to Fit in Your Fridge

Will Knight | Wired Magazine

Artificial intelligence programs typically are power guzzlers. New research shows how to generate computer vision from a simple, low-power chip.

hand gesture drawing iage credit: mit tech review

Powerful Computer Vision Algorithms are Now Small Enough to Run on Your Phone

Karen Hao | MIT Technology Review

Researchers have shrunk state-of-the-art computer vision models to run on low-power devices.

Privacy Preference Center