Tech Xplore

Mistaken correlations: Why it's critical to move beyond overly aggregated machine-learning metrics

MIT researchers have identified significant examples of machine-learning model failure when those models are applied to data ...
EurekAlert!

Multi-constraint reinforcement learning in complex robot environments

FPMCO decomposes multi-constraint RL into KL-projection sub-problems, achieving higher reward with lower computing than second-order rivals on the new SCIG robotics benchmark.
IEEE

DiMAT Materials Modeler (DiMM): An Interactive Framework for Materials Property Prediction and Optimization Using a Hybrid Machine Learning - Genetic Algorithm Approach

Abstract: We present DiMM (DiMAT Materials Modeler), an interactive framework that advances materials informatics through an effective integration of machine learning (ML) and genetic algorithms (GA).
IEEE

Optimization of Federated Learning Algorithm for Non-lID Data: Improvements to the FedDyn Algorithm

Abstract: This paper investigates the optimization of the FedDyn algorithm in Federated Learning (FL). Federated Learning is a distributed machine learning framework that enables model training on ...