Silas: High Performance, Explainable and Verifiable Machine Learning
This tool addresses the need for explainable and verifiable machine learning, particularly for users requiring dependable and transparent data analytics, though it appears incremental in its approach.
The paper introduces Silas, a classification tool designed to provide transparent and dependable data analytics by offering formal verification of decision trees against user specifications and guaranteed correctness in training, with implementation details for high-performance computation.
This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service. A focus of Silas is on providing a formal foundation of decision trees in order to support logical analysis and verification of learned prediction models. This paper describes the distinct features of Silas: The Model Audit module formally verifies the prediction model against user specifications, the Enforcement Learning module trains prediction models that are guaranteed correct, the Model Insight and Prediction Insight modules reason about the prediction model and explain the decision-making of predictions. We also discuss implementation details ranging from programming paradigm to memory management that help achieve high-performance computation.