Description

As Artificial Intelligence is becoming part of user-facing applications and directly impacting society, deploying AI reliably and responsibly has become a priority for Microsoft and several other industry leaders. Rigorous model evaluation and debugging and responsible decision-making are at the heart of responsible machine learning development and deployment. 

The Responsible AI Dashboard is an open-source framework for helping engineers to build excellent products that are responsible and reliable. It provides a single pane of glass that integrates together ideas and technology from several open-source tools in the areas of error analysis (Error Analysis), interpretability (InterpretML), fairness (Fairlearn), counterfactual analysis (DiCE), and causal decision making (EconML). 

The main goal is to further accelerate engineering processes in machine learning by enabling practitioners to design customizable workflows and tailor RAI dashboards that best fit with their scenario. Through the tool engineers can create end to end and fluid debugging experiences and are able to navigate seamlessly through error identification and diagnosis by using interactive visualizations that identify errors, inspect the data, generate global and local explanations models, and potentially inspect problematic examples. They can also customize the dashboard and use it to explore causal relationships in the data and take informed decisions in the real world. The dashboard is a central part the Responsible AI Toolbox, a larger open-source effort at Microsoft for aligning together Responsible AI tools and facilitating future tooling extensions from the data science community. 


Website: responsibleaitoolbox.ai 

Github repository: github.com/microsoft/responsible-ai-toolbox

Local ODSC chapter in Boston, USA


Instructor's Bio

 Besmira Nushi

Principal Researcher at Microsoft

Her interests lie at the intersection of human and machine intelligence focusing on Reliable Machine Learning and Human-AI Collaboration. In the last five years, she has made practical and scientific contributions on implementing and deploying Responsible AI tools for debugging and troubleshooting ML systems. Prior to Microsoft, Besmira completed her doctoral studies at ETH Zurich in 2016 on optimizing data collection processes for Machine Learning. 

 Mehrnoosh Sameki

Senior Technical Program Manager at Microsoft

Mehrnoosh is responsible for leading the product efforts on machine learning model understanding tools (machine learning interpretability, fairness, and reliability) within the Open Source and Azure Machine Learning platform. She has cofounded Fairlearn, Error Analysis, and Responsible-AI-toolbox open source repositories and has been a contributor to the InterpretML offering. She earned her PhD degree in computer science at Boston University, where she currently serves as an adjunct assistant professor, offering courses in responsible AI. Previously, she was a data scientist in the retail space, incorporating data science and machine learning to enhance customers’ personalized shopping experiences. 

Webinar

  • 1

    ON-DEMAND WEBINAR: Responsible AI Dashboard: A tool for operationalizing Responsible AI

    • Ai+ Training

    • Webinar recording

UPCOMING LIVE TRAINING

Register now to save 30%