Explainable Artificial Intelligence (XAI)

What is Explainable Artificial Intelligence (XAI)?

Explainable Artificial Intelligence (XAI) is an emerging field of study that aims to ensure that humans can understand how an intelligent automated system came to its outcome (i.e. prediction, decision, or action).

Artificial Intelligence (AI) plays an ever-increasing role in our everyday life and finds its way into more and more business applications in just about every industry. As Artificial Intelligence permeates into more facets of how we go about our life and business, we need to be able to trust that these intelligent systems are not only doing things right but also doing the “right thing”.

The current resurgence of Artificial Intelligence is mostly driven by Sub-Symbolic AI approaches such as Deep Neural Networks (DNN) and Machine Learning (ML). One of the most unfortunate consequences of this resurgence is the promotion of solutions that make “black boxes” out of such systems. In strange ways, we are drawn by this “unexplainable” way in which these intelligent systems make predictions of whether it is a picture of a cat or a dog. But in a business context, or worst in a life or death context such as healthcare, we not only expect but lawfully require that the decisions made be explainable. Why was this loan rejected? Why have you prescribed this medication? Clearly, if we are going to increasingly rely on Artificial Intelligence systems, we need them to be Explainable Artificial Intelligence (XAI) systems.

Building Artificial Intelligence applications do not need to be hard. One way to gain Explainable Artificial Intelligence is to use the Decision Model and Notation (DMN) standard. DMN makes it easy to build Explainable Artificial Intelligence (XAI) systems by allowing simple visual modeling of decision requirements and decision logic. These graphical visual representations are not only simple to read and interpret by humans, but they are also machine automatable. Using Trisotech Digital Enterprise Suite, you can build intelligent decision systems that can explain their answers.