Explainable AI (original) (raw)

  1. Home
  2. AI
  3. Trustworthy AI
  4. Explainable AI

Topics

To trust AI systems, explanations can go a long way. We’re creating tools to help debug AI, where systems can explain what they’re doing. This includes training highly optimized, directly interpretable models, as well as explanations of black-box models and visualizations of neural network information flows.

Our work

IBM RESEARCH_BlogPost_sep28-12.jpg

Blog_RAG post.jpg

Publications

View all publications

CausalityFairness, Accountability, TransparencyHealthcare and Life SciencesAI for Business Automation