Explaining the Challenges of Accountability in Machine Learning Systems Beyond Technical Obstacles
Srinivas Kumar Palvadi · Advances in bioinformatics and biomedical engineering book series · 2023
The ability to make a note regarding machine learning systems decisions for people is becoming increasingly sought after, particularly in situations where decisions have significant repercussions for those affected and where capability in terms of maintaining is required. To increase comprehension based on referred to as “black box” mechanism, explaining ability is frequently cited as a technical obstacle in the design of ML systems and decision procedures. The quantities that ML systems aim to optimize must be specified by their users. This leads to the revealing of policy trade-offs that may have previously been hidden or implicit. Important decisions, as well as judgments, help what may need to be explicitly discussed in public debate as ML's use in policy expands.