A new programme aims to boost MIT's AI hardware innovation in the future | Technology
|A new programme aims to boost MIT's AI hardware innovation in the future|
A new programme will support the development of next-generation artificial intelligence devices
MIT's AI hardware project was launched over the next decade, with five startups developing AI technology.
The MIT AI Hardware Project is a new academic and industry collaboration to identify and develop hardware and software translation technologies for the AI and quantum eras. A collaboration between MIT's School of Engineering and MIT's Schwarzman School of Computing, including the School's Microsystems Technology, Software, and Unit Labs, an interdepartmental effort aimed at creating technologies for cloud computing and computer computing Offers advanced energy efficiency systems.
"Focusing on the creation, research, and design of artificial intelligence devices is important to meet the needs of the world's most advanced hardware, architectures, and systems," said Ananta Chandrakasan, Dean of MIT's School of Engineering and Professor of Electrical Engineering and Venezuela. "Bosch" Knowledge sharing between industry and academia is critical to the future of high-performance computing."
Based on usage-inspired research involving materials, hardware, circuits, algorithms, and software, the MIT AI Hardware Initiative calls for bringing together MIT and industry researchers to facilitate the transfer of needed knowledge to reality the world's technological solutions. The program expands to materials and devices, as well as architectures and algorithms that enable energy-efficient and sustainable high-performance computing.
"As AI systems become more complex, new solutions are urgently needed to enable more advanced applications," said Daniel Huttenlicher, Dean of MIT's Schwarzman School of Computing, and Henry Ellis, Professor of Electrical Engineering and Computer Science Warren said. "Our goal is to create realistic technological solutions and lead the way in AI technology in both hardware and software."
Companies from a wide range of industries, including chip manufacturing, semiconductor manufacturing equipment, artificial intelligence and computing services, and information systems research and development companies, are founding members of the program. These companies represent a diverse ecosystem nationally and internationally, and will collaborate with MIT faculty, staff and students to help shape a vibrant future for our planet through cutting-edge AI research.
The five founding members of the MIT AI Hardware Initiative
Amazon, a global technology company whose inventions include the Kindle, Amazon Echo, Fire TV, and Astro;
A world leader in the design and manufacture of analog devices, analog and hybrid integrated circuits, and digital signal processors.
ASML is a leading innovator in the semiconductor industry, providing hardware, software and services to chipmakers to create huge patterns on silicon wafers through lithography;
NTT Research, an affiliate of NTT, conducts fundamental research to advance reality in game-changing ways that improve lives and illuminate our global future; and TSMC, the world's leading semiconductor foundry.
MIT's AI Hardware Initiative will create a roadmap for transforming AI hardware technology. Wherever MIT.nano is located, using state-of-the-art university nanofabrication facilities, the program will create a unique environment for AI device research.
"We are all terrified of the seemingly superhuman capabilities of today's artificial intelligence systems, yet their energy costs are growing rapidly and sustainably," said Donner, a professor in MIT's Department of Electrical Engineering and Computer Science. "Continued advances in AI will New, more energy-efficient systems are needed. This will require innovation across the entire spectrum of abstraction, from components and hardware to systems and software. The software is uniquely positioned to contribute to this effort."
The plan will prioritize the following:
- Analog Neural Network
- New CMOS roadmap design;
- Heterogeneous integration of AI systems;
- 3D unicorn artificial intelligence system;
- Non-volatile analog storage devices;
- Software and hardware joint design;
- Intelligence is at the edge.
- Smart sensor
- Energy-saving artificial intelligence;
- Intelligent Internet of Things (IIoT);
- Neural computing;
- Edge security with AI;
- Quantum artificial intelligence
- Wireless technology
- Hybrid cloud computing; and
- High performance account
Senior Research Scientist Odd Oliva said: "We are living in an era where paradigm shifts in hardware, communications and computing systems are discovering critical to finding sustainable solutions - and we are proud to present solutions to the world and future generations." Director of the Provincial Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) and Strategic Industrial Engagement.
The new project is led by Jesus del Alamo and Oud Oliva, with Ananta Chandrakasan as acting chair.
Source: MIT News, Schwarzman School of Computing, Direct News 99