View Full Version : InterpretML, open-source software toolkit for explaining black box AI, Microsoft Corporation, Redmond, Washington, USA
Airicist
16th May 2020, 18:22
Developer - Microsoft Corporation (https://pr.ai/showthread.php?4302)
interpret.ml (http://interpret.ml)
interpretm.ai (http://interpretml.ai)
github.com/interpretml (https://github.com/interpretml)
Airicist
16th May 2020, 18:32
Article "Microsoft open-sources lnterpretML for explaining black box AI (https://venturebeat.com/2019/05/10/microsoft-open-sources-lnterpretml-for-explaining-black-box-ai)"
by Khari Johnson
May 10, 2019
Airicist
16th May 2020, 18:35
Article "InterpretML: A Unified Framework for Machine Learning Interpretability (https://arxiv.org/pdf/1909.09223.pdf)"
by Harsha Nori, Samuel Jenkins, Paul Koch, Rich Caruana
September 19, 2019
Airicist
16th May 2020, 18:36
"Explain Your Model with Microsoft’s InterpretML (https://medium.com/analytics-vidhya/explain-your-model-with-microsofts-interpretml-5daab1d693b4)"
Feb 27, 2020
Airicist
16th May 2020, 18:38
https://youtu.be/WwBeKMQ0-I8
How to explain models with IntepretML Deep Dive
May 16, 2020
With the recent popularity of machine learning algorithms such as neural networks and ensemble methods, etc., machine learning models become more like a 'black box', harder to understand and interpret. To gain the stakeholders' trust, there is a strong need to develop tools and methodologies to help the user to understand and explain how predictions are made. In this video, you learn about our open source Machine Learning Interpretability toolkit, InterpretML, which incorporates the cutting-edge technologies developed by Microsoft and leverages proven third-party libraries. InterpretML introduces a state-of-the-art glass box model (EBM), and provides an easy access to a variety of other glass box models and blackbox explainers.
Airicist
16th May 2020, 18:40
https://youtu.be/MREiHgHgl0k
The science behind InterpretML: explainable boosting machine
May 16, 2020
Learn more about the research that powers InterpretML from Explainable Boosting Machine creator, Rich Caurana (https://www.linkedin.com/in/rich-caruana-a4235a91) from Microsoft Research