Summary
This chapter approached XAI using moral, technical, ethical, and bias perspectives.
The trolley problem transposed to SDC autopilot ML algorithms challenges automatic decision-making processes. In life and death situations, a human driver faces near-impossible decisions. Human artificial intelligence algorithm designers must find ways to make autopilots as reliable as possible.
Decision trees provide efficient solutions for SDC autopilots. We saw that a standard approach to designing and explaining decision trees provides useful information. However, it isn't enough to understand the decision trees in depth.
XAI encourages us to go further and analyze the structure of decision trees. We explored the many options to explain how decision trees work. We were able to analyze the decision-making process of a decision tree level by level. We then displayed the graph of the decision tree step by step.
Still, that was insufficient in finding a way to minimize the deaths that can happen in situations where killing a pedestrian or the passengers of an SDC cannot be avoided. We introduced some basic rules to simulate AI bias and ethics.
Finally, we introduced alerts that the SDC's autopilot manuals recommend, minimizing encounters with life and death situations.
In this chapter, we traveled the tough journey from technical certainty to healthy moral doubt. We provided AI autopilots with the machine emotional maturity that can save lives by implementing the "fear" of accidents in our SDC autopilots.
In this chapter, we got our hands dirty by developing XAI decision trees. In Chapter 3, Explaining Machine Learning with Facets, we will explore Facets to drill down into datasets.
