Improving Machine Learning Test and Evaluation with MLTE

Machine learning (ML) models commonly experience issues when integrated into production systems. In this podcast, researchers from the Carnegie Mellon University Software Engineering Institute and the U.S. Army AI Integration Center (AI2C) discuss Machine Learning Test and Evaluation (MLTE), a new tool that provides a process and infrastructure for ML test and evaluation. MLTE can aid organizations across the DoD in more effectively negotiating, documenting, and evaluating model and system qualities.