Mark Anderson | IEEE Spectrum
AI researchers have been using AI neural networks to help design better and faster AI neural networks. Applying AI in pursuit of better AI has, to date, been a largely academic pursuit—mainly because this approach requires tens of thousands of GPU hours. If that’s what it takes, it’s likely quicker and simpler to design real-world AI applications with the fallible guidance of educated guesswork.
However, a team of MIT researchers, including AI Hardware principal investigator Song Han, have been working on a so-called “Proxyless neural architecture search” algorithm that can speed up the AI-optimized AI design process by 240 times or more. That would put faster and more accurate AI within practical reach for a broad class of image recognition algorithms and other related applications.
Complete article from IEEE Spectrum.
Explore
Energy-Efficient and Environmentally Sustainable Computing Systems Leveraging Three-Dimensional Integrated Circuits
Wednesday, May 14, 2025 | 12:00 - 1:00pm ET
Hybrid
Zoom & MIT Campus
Analog Compute-in-Memory Accelerators for Deep Learning
Wednesday, April 30, 2025 | 12:00 - 1:00pm ET
Hybrid
Zoom & MIT Campus
Agile Design of Domain-Specific Hardware Accelerators and Compilers
Wednesday, February 12, 2025
Hybrid
Zoom & MIT Campus