IBM Takes Major Step in Breaking Open the Black Box of AI

Alonzo Simpson
September 21, 2018

"It's time to translate principles into practice", Beth Smith, general manager of Watson AI at IBM, said in a news release. "It's created to translate algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education", they outlined. "We are giving new transparency and control to the businesses who use AI and face the most potential risk from any flawed decision making", senior vice president of Cognitive Solutions at IBM, David Kenny said in a statement.

Explanations are provided in easy to understand terms, showing which factors weighted the decision in one direction vs. another, the confidence in the recommendation, and the factors behind that confidence. While other open-source resources have focused exclusively on checking for bias in training data, the IBM AI Fairness 360 toolkit created by IBM Research will help check for and mitigate bias in AI models. It also provides a record of model accuracy, performance, fairness, and lineage, which IBM says may be helpful for GDPR compliance. The software will feature visual dashboards for providing the breakdown of automated decisions.

Kanye West Rants Against Drake, Nick Cannon Over Kim Kardashian Lyrics
Now I done told you I didn't tell Pusha no information about your baby, baby mother, nothing like that. Nick and Kim dated back in their mid 20s, and Nick excitedly reminisced about her body, saying.

In an effort to fight bias in artificial intelligence, IBM is launching a new tool capable of analysing how and why algorithms make the decisions they do in real time. It is an open-source library to assist in targeting and removing bias within data sets and machine-learning models. Called AI Fairness 360 (AIF360), this product by IBM is a comprehensive open-source toolkit of metrics to check for unwanted bias in datasets, machine learning models, and state-of-the-art algorithms. "AIF360 is a bit different from now available open source efforts1 due its focus on bias mitigation (as opposed to simply on metrics), its focus on industrial usability, and its software engineering", wrote Kush Varshney, principal research staff member and manager at IBM Research.

Other reports by

Discuss This Article