Category Archives: Explanations

Explainability and Interpretability

Explainability of decisions produced by machines is one of the hottest topic these days (see XAI). Explainable AI usually makes decisions using a complicated black box model, and uses a second (posthoc) model created to explain what the first model … Continue reading

Posted in Artificial Intelligence, Explanations | Leave a comment

How can we persuade people to trust an algorithm?

On Dec. 4 Andrew Ng listed several important techniques  that can persuade people to trust an algorithm. “Trust isn’t just about convincing others that our solution works. I use techniques like these because I find it at least as important … Continue reading

Posted in Artificial Intelligence, Explanations | Leave a comment

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

Explainable Decisions

Majority of decision modeling experts agree that decision models producing business decisions should be able to explain why these decisions were made. Silvie Spreeuwenberg even wrote that “Advice Without Explanation Is Not Very Intelligent“. Tomorrow FICO will run a special … Continue reading

Posted in Decision Modeling, Explanations | 2 Comments