Many teams are building unstructured models but are unable to monitor or explain their model decisions. Unraveling models through natural language processing (NLP) or computer vision (CV) monitoring is essential for interpretability and transparency.
Watch this webinar to learn:
AI Explained is our new AMA series featuring experts on the most pressing issues facing AI and ML teams.
Can’t attend live? Recordings will be available to all registrants after the event.
Josh has been a Fiddler for three years and currently manages its Data Science team. During this time he developed a modular framework to extend explainability to complex model form-factors, such as those with multi-modal inputs. He previously applied deep learning to instrument calibration and signal processing problems in the biotech tools space after outgrowing a career as an experimental nuclear physicist.
Prior to Fiddler, he was a Principal Scientist at Amazon AWS AI and LinkedIn AI, where he led the fairness, explainability, privacy, and model understanding initiatives. Krishnaram received his Ph.D. in Computer Science from Stanford University in 2006. He serves regularly on the program committees of KDD, WWW, WSDM, and related conferences. His work has been recognized through awards at NAACL, WWW, SODA, CIKM, ICML AutoML workshop, and Microsoft’s AI/ML conference (MLADS). He has published 50+ papers, with 4500+ citations and filed 150+ patents (70 granted).
Many teams are building unstructured models but are unable to monitor or explain their model decisions. Unraveling models through natural language processing (NLP) or computer vision (CV) monitoring is essential for interpretability and transparency.
Watch this webinar to learn:
AI Explained is our new AMA series featuring experts on the most pressing issues facing AI and ML teams.
Can’t attend live? You should still register! Recordings will be available to all registrants after the event.
Josh has been a Fiddler for three years and currently manages its Data Science team. During this time he developed a modular framework to extend explainability to complex model form-factors, such as those with multi-modal inputs. He previously applied deep learning to instrument calibration and signal processing problems in the biotech tools space after outgrowing a career as an experimental nuclear physicist.
Prior to Fiddler, he was a Principal Scientist at Amazon AWS AI and LinkedIn AI, where he led the fairness, explainability, privacy, and model understanding initiatives. Krishnaram received his Ph.D. in Computer Science from Stanford University in 2006. He serves regularly on the program committees of KDD, WWW, WSDM, and related conferences. His work has been recognized through awards at NAACL, WWW, SODA, CIKM, ICML AutoML workshop, and Microsoft’s AI/ML conference (MLADS). He has published 50+ papers, with 4500+ citations and filed 150+ patents (70 granted).