A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) demonstrates a novel approach to training AI models that significantly reduces computational costs and energy consumption. The method, called ‘Liquid Neural Networks,’ allows models to learn continuously from new data streams without requiring complete retraining from scratch. This approach mimics more adaptive, biological learning processes and could make advanced AI more accessible by lowering the hardware and energy barriers to entry. The research highlights a shift towards developing more efficient and sustainable AI systems as model sizes and their environmental impacts grow. For the full details, read the complete article at https://technologyreview.com/2024/03/15/ai-training-method-cuts-cost-energy.