Green Learning: Introduction, Examples and Outlook
It addresses sustainability and trust issues in AI for researchers and practitioners, though it appears incremental as an alternative approach building on existing statistical tools.
The paper introduces Green Learning (GL) as an alternative paradigm to deep learning, tackling the high carbon footprint and lack of transparency in AI by offering low-energy, small-model solutions with logical decision-making, achieving performance comparable to state-of-the-art deep learning in some applications.
Rapid advances in artificial intelligence (AI) in the last decade have largely been built upon the wide applications of deep learning (DL). However, the high carbon footprint yielded by larger and larger DL networks becomes a concern for sustainability. Furthermore, DL decision mechanism is somewhat obsecure and can only be verified by test data. Green learning (GL) has been proposed as an alternative paradigm to address these concerns. GL is characterized by low carbon footprints, small model sizes, low computational complexity, and logical transparency. It offers energy-effective solutions in cloud centers as well as mobile/edge devices. GL also provides a clear and logical decision-making process to gain people's trust. Several statistical tools have been developed to achieve this goal in recent years. They include subspace approximation, unsupervised and supervised representation learning, supervised discriminant feature selection, and feature space partitioning. We have seen a few successful GL examples with performance comparable with state-of-the-art DL solutions. This paper offers an introduction to GL, its demonstrated applications, and future outlook.