TagsArticle Source
Explainable AI
- Speaker: Dr. David Aha, Acting Director, Navy Center for Applied Research in AI, U.S. Naval Research Laboratory
Abstract
Dramatic success in machine learning (ML) has led to a new wave of artificial intelligence applications (e.g., transportation, security, medicine, finance, and defense) that offer tremendous benefits. However, current ML cannot explain its decisions and actions to human users. DARPA’s Explainable Artificial Intelligence (XAI) program endeavors to create AI systems that’s learned models and decisions can be understood and appropriately trusted by end users. Realizing this requires methods for learning more explainable models, designing effective explanation interfaces, and understanding the psychological requirements for effective explanations. This talk will summarize the XAI program and present highlights from the first phase of the program.