H2O.ai to Share the Latest Advancements in Machine Learning Interpretability
NEW YORK and MOUNTAIN VIEW, Calif., April 25, 2018 /PRNewswire/ — H2O.ai, the open leader in AI, announced today that Patrick Hall, senior director of product at H2O.ai, adjunct professor and co-author of the recent O’Reilly booklet “An Introduction to Machine Learning Interpretability,” will be speaking at the upcoming NYC Big Data Science Meetup, held in conjunction with O’Reilly AI, on April 30 about interpretable machine learning techniques. Hall will be joined by Navdeep Gill, engineer and data scientist at H2O.ai, who has made significant technical contributions to H2O.ai’s unique interpretability capabilities in its enterprise product, Driverless AI.
The talk titled, “Building Explainable Machine Learning Systems: The Good, the Bad, and the Ugly,” will help data scientists make interpretable machine learning projects a success by describing fundamental technical challenges they will face in building an interpretable machine learning system, define the real-world value proposition of approximate explanations for exact models, and then outline viable techniques for debugging, explaining, and testing machine learning models.
NYC Big Data Science Meetup
When: Monday, April 30, 2018, 6:30-8:00pm ET
Where: New York Hilton Midtown, 1335 6th Avenue, New York
Topic: The talk will include a complete discussion on MLI with the good news that building fair, accountable, and transparent machine learning systems is possible. The bad news: it’s harder than many blogs and software package docs report it to be. The truth is that nearly all interpretable machine learning techniques generate approximate explanations, that the fields of eXplainable AI (XAI) and Fairness, Accountability and Transparency in Machine Learning (FAT/ML) are very new, and that few best practices have been widely agreed upon. This combination can lead to some ugly outcomes. Plenty of guidance on when, and when not, to use these techniques will also be shared, and the session will conclude by providing guidelines for testing generated explanations themselves for accuracy and stability.
Copies of the booklet co-authored by Patrick Hall and Navdeep Gill will be handed out at the event, or can be downloaded here: http://www.oreilly.com/data/free/an-introduction-to-machine-learning-interpretability.csp
Register for the NYC Big Data Science Meetup: https://www.meetup.com/NYC-Big-Data-Science/events/249437629/
Meet H2O.ai at O’Reilly AI
H2O.ai is fostering a grassroots movement of systems engineers, data scientists, data developers and predictive analysts to move machine learning forward. Its enterprise product Driverless AI provides organizations with the intelligence of a Kaggle Grandmaster in a box. Stop by Booth #14 at O’Reilly AI to meet H2O.ai and learn more. A free 21-day trial of Driverless AI with interpretability is currently available here: https://www.h2o.ai/driverless-ai/.
H2O.ai is the leader in AI with its visionary open source platform, H2O. Its mission is to democratize AI for all. H2O.ai is transforming the use of AI within all software with its category-creating visionary open source machine learning movement. More than 12,600 companies use open-source H2O in mission-critical use cases for Finance, Insurance, Healthcare, Retail, Telco, Sales, and Marketing. H2O.ai recently launched Driverless AI that uses AI to do AI in order to provide an easier, faster and cheaper means of implementing data science. In February 2018, Gartner named H2O.ai, as a Leader in the 2018 Magic Quadrant for Data Science and Machine Learning Platforms. H2O.ai partners with leading technology companies such as NVIDIA, IBM, AWS, Azure and Google and is proud of its growing customer base which includes Capital One, Progressive Insurance, Comcast, Walgreens and Kaiser Permanente. For more information and to learn more about how H2O.ai is transforming business processes with intelligence, visit www.h2o.ai.