Silas: A high-performance machine learning foundation for logical reasoning and verification

This paper introduces a new high-performance machine learning tool named Silas, which is built to provide more transparent, dependable and efficient data analytics service. We discuss the aspects of Silas demonstrate advantage in its predictive computational performance. show that several customised algorithms yield better predictions significantly shorter time compared state-of-the-art. Another focus on providing formal foundation decision trees support logical analysis verification learned prediction models. illustrate potential capabilities fusion reasoning by showcasing applications three directions: model against user specifications, training correct-by-construction models, explaining decision-making predictions.