Category Archives: Explanations

DARPA Explainable AI Program

Defense Advanced Research Projects Agency Explainable AI (XAI) program:

Posted in Artificial Intelligence, Explanations, Machine Learning | Leave a comment

IBM Research launches explainable AI toolkit

IBM Research introduced AI Explainability 360, an open source collection of state-of-the-art algorithms that use a range of techniques to explain AI model decision-making. “That’s fundamentally important, because we know people in organizations will not use or deploy AI technologies … Continue reading

Posted in Artificial Intelligence, Explanations | Leave a comment

Explaining Decision Optimization Recommendations

Explainability is a hot topic. Decision models are used to trigger recommendations such as “accept” or “refuse” a loan, but they also need to explain WHY they recommended certain decisions. Alain Chabrier from IBM DecisionOptimization team uses Portfolion Allocation problem … Continue reading

Posted in Explanations, Optimization | Leave a comment

Statistical Methods with Domain-based Models

This WSJ article gives examples when ML-based solutions have been enhanced by the inclusion of pre-defined domain-specific models. “Machine learning is a statistical modeling technique, which finds and correlates patterns between inputs and outputs without necessarily capturing their cause-and-effect relationships. … Continue reading

Posted in Business Analytics, Explanations, Machine Learning | Leave a comment

XAI – Explainable Artificial Intelligence

Two new articles about explainable AI: Link1 Link2

Posted in Artificial Intelligence, Explanations | Leave a comment

Google’s What-If Tool for Machine Learning Models

Building effective machine learning (ML) systems means asking a lot of questions. It’s not enough to train a model and walk away. Instead, good practitioners act as detectives, probing to understand their model better: How would changes to a datapoint affect … Continue reading

Posted in Explanations, Machine Learning | Leave a comment

Decision Automation and Explanations

Prof. Gene Freuder wrote a position paper “Complete Explanations”: “The position taken here is that it can be worthwhile to start with truly complete explanations and abstract and limit from there. The goal is to provide a high-level “big picture” of … Continue reading

Posted in Decision Modeling, Explanations, Human-Machine Interaction, Optimization | Leave a comment