Assessing and implementing trustworthy AI across multiple dimensions
Abigail Goldsteen1, Ariel Farkash1 and Michael Hind2, 11IBM Research, Haifa, Israel, 22IBM Research, Yorktown Heights, New York, NY, United States
Abstract
Artificial intelligence (AI) systems have become more and more prevalent in everyday life, especially in enterprise settings. These systems have grown increasingly more accurate and efficient, but at the same time more complex and less understandable. Broad adoption of AI systems requires humans to trust them. This depends on the ability to ensure that AI systems are fair, robust, explainable, accountable, and respectful of the privacy of individuals and will cause no harm. To this end, many tools and techniques ...
Get Ethics in Online AI-Based Systems now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
