A Review on Artificial Intelligence (AI) Transparency in Black-Box Models (BBM)

Artificial Intelligence (AI) uses systems and machines to simulate human intelligence and solve common real-world problems. Machine learning and deep learning are Artificial intelligence technologies that use algorithms to predict outcomes more accurately without relying on human intervention. AI systems are often described as “black boxes” that must be made scriptable for oversight. This view tends to accompany a technical framing of the problem, under which some present or future approach can make AI systems transparent. In this paper, I argue that what the law expects from “transparency” is not something that can be provided by purely legal means. Explainable Artificial Intelligence (XAI) is a term that refers to Artificial Intelligence (AI) that can provide explanations for their decision or predictions to human users. XAI aims to increase the transparency, trustworthiness and accountability of AI system, especially when they are used for high-stakes application such as healthcare, finance or security. This paper offers systematic literature review of XAI approaches with different application and observes 91 recently published articles describing XAI development and applications in healthcare. They have moved from displaying a simple, causality-driven operability, where one can look for what triggered the decision and find it. This is an effect that can be described as behavior resulting directly from a single action or cause. With today's AI, these triggers can raise their heads and exist in the system, but cannot easily be seen; in fact, they may have hidden triggers that we can’t label as a cause. There are correlations and causation frequently mixed up in complex settings. Such nontransparent environments lead to decisions in AI, despite the sophistication of today's methodology not being interpretable to the user interacting with the system; these might be internal agents or external agents. This results in a situation where decision-making is non-transparent, undermining human control in AI and hence posing considerable risks to the safety, operation, marketing, and branding of AI. It is these risks that we describe as the Black Box problem.