Learning to grow machine-learning models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.
MIT-led teams win National Science Foundation grants to research sustainable materials
The teams will work toward sustainable microchips and topological materials as well as socioresilient materials design.
A new chip for decoding data transmissions demonstrates record-breaking energy efficiency
The chip, which can decipher any encoded signal, could enable lower-cost devices that perform better while requiring less hardware.
Computers that power self-driving cars could be a huge driver of global carbon emissions
Study shows that if autonomous vehicles are widely adopted, hardware efficiency will need to advance rapidly to keep computing-related emissions in check.
Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs
New technique significantly reduces training and inference time on extensive datasets to keep pace with fast-moving data in finance, social networks, and fraud detection in cryptocurrency.
Breaking the scaling limits of analog computing
New technique could diminish errors that hamper the performance of super-fast analog optical neural networks.
Green computing is super
MIT Lincoln Laboratory's new supercomputing facility reduces energy impacts