Machine Learning Algorithm
Machine learning algorithms are computational tools designed to learn patterns from data and make predictions or decisions without explicit programming. Current research emphasizes improving algorithm efficiency and interpretability, exploring various model architectures such as decision trees, neural networks (including LSTMs and GRUs), random forests, and support vector machines, as well as novel approaches based on information theory and Bayesian optimization. These advancements are impacting diverse fields, from healthcare (disease prediction, medical image analysis) and finance (option pricing) to engineering (combustion control, structural anomaly detection) and environmental science (contaminant monitoring), improving accuracy, efficiency, and decision-making in numerous applications.
Papers
An effective and efficient green federated learning method for one-layer neural networks
Oscar Fontenla-Romero, Bertha Guijarro-Berdiñas, Elena Hernández-Pereira, Beatriz Pérez-Sánchez
DMC4ML: Data Movement Complexity for Machine Learning
Chen Ding, Christopher Kanan, Dylan McKellips, Toranosuke Ozawa, Arian Shahmirza, Wesley Smith