MIT launches interdisciplinary program to drive innovation in AI hardware

MIT has launched a new academia-industry partnership called the AI ​​Hardware Program aimed at boosting research and development.

“To meet the demands of the world’s evolving devices, architectures and systems, it’s important to focus on manufacturing, researching and designing AI hardware,” said Vannevar Bush, professor of electrical engineering at the MIT School of Engineering. Anantha Chandrakasan says. And computer science.

“Knowledge sharing between industry and academia is essential for the future of high performance computing.”

The first members of the program are five people.

  • Amazon
  • Analog Devices
  • ASML
  • NTT Research
  • TSMC

As the diversity of inaugural members shows, this program is aimed at interdisciplinary efforts.

“As AI systems become more sophisticated, new solutions are urgently needed to enable more sophisticated applications and deliver better performance,” said Henry Ellis Warren, Dean of the MIT Schwarzman College of Computing. Daniel Huttenlocher, a professor of electrical engineering and computer science, commented.

“Our purpose is to devise real-world technology solutions and lead the development of AI technology in hardware and software.”

The main goal of this program is to help create more energy efficient systems.

“We are all in awe of the superhuman capabilities of today’s AI systems, but this is accompanied by rapidly increasing and unsustainable energy costs,” MIT’s electrical engineering and Jesús del Alamo, a donor professor at the School of Computer Science, explained.

“Continuous advances in AI require new, much more energy-efficient systems that require innovation across the abstraction stack, from materials and devices to systems and software. This program is in a unique position to contribute to this quest. “

Other important areas of research are:

  • Analog neural network
  • New CMOS design
  • Heterogeneous integration of AI systems
  • Monolithic-3DAI system
  • Analog non-volatile memory device
  • Co-design of software and hardware
  • Edge intelligence
  • Intelligent sensor
  • Energy efficient AI
  • Intelligent Internet of Things (IIoT)
  • Neuromorphic computing
  • AI edge security
  • Quantum AI
  • Wireless technology
  • Hybrid cloud computing
  • High performance computing

It’s an exhaustive list and an ambitious project. However, the AI ​​hardware program is off to a great start with the first members providing important talent and expertise in their respective fields.

“We live in an era where the discovery of paradigm shifts in hardware, system communications and computing has become essential to finding sustainable solutions. We are proud to deliver it to the world and the next generation. That’s the solution I’m thinking of, “said Eau de Oliver, senior research scientist. He is the Director of Strategic Industrial Engagement at the MIT Schwartzmann Computing University at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).

The program is co-led by Jesús del Alamo and Aude Oliva. Chaired by Anantha Chandrakasan.

For more information on AI hardware programs here..

(Photo courtesy of Nejc Soklič on Release the splash).

Want to know more about AI and big data from industry leaders? check out AI & Big Data Expo.. The next event in the series will take place in Santa Clara, May 11-12, 2022, in Amsterdam, September 20-21, 2022, and in London, December 1-2, 2022.

See other upcoming enterprise technology events and webins with TechForge here.

tag: ai, ai hardware program, Amazon, Analog devices, artificial intelligence, asml, hardware, Mitt, ntt research, research, tsmc MIT launches interdisciplinary program to drive innovation in AI hardware

Back to top button