Research / Point of view
AI systems are increasingly being entrusted with making critical decisions. Many of these decisions might have a considerable impact on businesses and even our lives. Machine learning (ML) is at the core of these decision systems.
The evolution of deep learning has resulted in a tremendous increase in the accuracy of these decisions, but the machine learning models that these AI systems are based on are mostly ‘black boxes’. The human mind, however, is not comfortable with trusting a system that makes a decision without letting it into the rationale behind this. And where trust is in deficit, acceptance is difficult.
Explainable AI (XAI) refers to a set of tools and techniques that help us humans interpret and trust the decisions made by ML models.