Accurate and transparent AI models are possible

12/05/2023 | Harvard Business Review

New research compares the performance of white-box artificial intelligence (AI) models with their black-box counterparts to identify which is more accurate. In simple terms, the difference between white and black box models relates to the complexity of the rules and parameters used to inform their outputs. White box models contain only a few straightforward rules with limited parameters, making them more transparent and easier to limit biases. On the other hand, black box models can have thousands of rules and even billions of parameters. But which approach works best? 

According to the research, "in many cases, simple, interpretable AI models perform just as well as black box alternatives — without sacrificing the trust of users or allowing hidden biases to drive decisions."

Read Full Story
Artificial Intelligence, AI

What is this page?

You are reading a summary article on the Privacy Newsfeed, a free resource for DPOs and other professionals with privacy or data protection responsibilities helping them stay informed of industry news all in one place. The information here is a brief snippet relating to a single piece of original content or several articles about a common topic or thread. The main contributor is listed in the top left-hand corner, just beneath the article title.

The Privacy Newsfeed monitors over 300 global publications, of which more than 4,350 summary articles have been posted to the online archive dating back to the beginning of 2020. A weekly roundup is available by email every Friday.

Freevacy has been shortlisted in the Best Educator category.
The PICCASO Privacy Awards recognise the people making an outstanding contribution to this dynamic and fast-growing sector.