We are excited to explore further how other AI models, like LLMs, can be trained more efficiently to achieve substantial reductions in AI-related carbon emissions.

This is achieved by decorrelating layer inputs using an iterative decorrelation method initially described in Ahmad et. al. (2022).

As AI adoption becomes more widespread, so do concerns about its energy consumption. Our latest paper proposes a method to train AI models more efficiently. The method reduces energy use by more than half when training a ResNet-18 model on ImageNet.