The Sustainable Machine Learning research group, led by Jun.-Prof. Dr. David Kappel, is dedicated to investigating the computational complexity of machine learning algorithms, in order to significantly reduce their power consumption while maintaining task performance.
Our Mission
Our mission is to develop state-of-the-art machine learning models that scale to real-world problems while being energy efficient. These models are based on the core design principles of sparsity and asynchrony and take inspiration from biology/neuroscience.
Modern machine learning (ML) architectures consume unprecedented amounts of energy, with a single training session often exceeding the energy and carbon footprint of a car over its entire lifetime. At the current rate of growth, ML models could overtake the transport sector in the global energy balance in 10-20 years. Biological brains, on the other hand, are extremely energy efficient, demonstrating that efficient learning systems exist in principle. The Sustainable Machine Learning group identifies the mechanisms that enable the remarkable energy efficiency of biological brains and explores new approaches to significantly reduce the energy footprint of machine learning using hybrid ML/bio-inspired models.
Research projects