A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) demonstrates a novel approach to AI training that significantly reduces energy consumption. The method, called ‘Liquid Neural Networks,’ mimics the adaptive, efficient learning processes found in biological brains, allowing AI models to learn from fewer examples and with less computational power. Researchers report energy savings of up to 80% compared to traditional deep learning methods on certain tasks, without sacrificing accuracy. This breakthrough could make advanced AI more accessible and sustainable, particularly for deployment on edge devices with limited resources. The full details of the research are available in the published paper. Read the full article at https://technologyreview.com/2024/05/15/liquid-neural-networks-energy-efficient-ai.