Introduction to Explainable AI

Paper - 1, Measuring the Quality of Explanations: The System Causability Scale

  • With the current advancements in Machine Learning, and AI. It is not possible to develop autonomous systems which can learn.
    • But this also leads to opaques in terms of their performance, and under what circumstances or conditions leads to change in their observation and performance.
    • It becomes certainly important in critical systems like Medical Imaging, or self driving car, or automatic flight systems.
    • It does not foster trust, acceptance and the most important responsibility.
  • Explainable AI aims to