AI Explainability 360: Impact and Design
- Vijay Arya
- Rachel Bellamy
- et al.
- 2022
- IAAI 2022
Michael Hind is a Distinguished Research Staff Member in the IBM Research AI department in Yorktown Heights, New York. His current research passion is in the general of area of Trusted AI, focusing on the fairness, explainability, transparency, and the goverance of AI systems. He currently leads the FactSheets project at IBM Research.
Michael has led dozens of researchers focusing on programming languages, software engineering, cloud computing, and tools for AI systems. Michael's team has successfully transferred technology to various parts of IBM and launched several successful open source projects, Jikes RVM, X10, WALA, OpenWhisk, and more recenty AI Fairness 360 and AI Explainability 360. After receiving his Ph.D. from NYU in 1991, Michael spent 7 years as an assistant/associate professor of computer science at SUNY - New Paltz.
Michael is an ACM Distinguished Scientist, and a member of IBM's Academy of Technology. He has co-authored over 50 publications, served on over 50 program committees, and given many keynotes and invited talks at top universities, conferences, and government settings. His 2000 paper on Adaptive Optimization was recognized as the OOPSLA'00 Most Influential Paper and his work on Jikes RVM was recognized with the SIGPLAN Software Award in 2012.
Check out these open source and research projects
Invited Talks/Panels/Interviews
AI Safety and Robustness in Finance workshop (invited talk & panel), ICAIF'23 (ACM International Conference on AI in Finance), Brooklyn, NY, November 27, 2023
Nassau Country TRACT Teacher Center's Technology Conference, November 15, 2023
Trustworthy AI: Challenges and Opportunities (keynote), 2nd SNAS Annual Academic Conference, Fairleigh Dickinson University, Madison, NJ, Oct 6, 2023
Presidential Symposium, Navigating the AI Revolution: Definitions and the Impact on Workforce Across Industries, (panel), Hofstra University, September 28, 2023 (video)
BSA Congressional Briefing: Everyday AI: Managing AI Risk Today (panel), September 26, 2023
Cornell University, Public Interest Technology Class, AI Trends, Challenges, and the Role of Public Policy, guest lecture, August 1, 2023
BSA Congressional Briefing: AI in Financial Services (panel), June 21, 2023
FactSheets: Increasing AI Transparency, Enabling Governance, and Assessing Risk (invited talk), SEC Quant Seminar, June 8, 2023
AI in the Built World: Who Should Be The Adults in The Room? (panel), Cherre Data Summit, May 17, 2023
FactSheets: Increasing AI Transparency, Enabling Governance, and Assessing Risk (keynote), Trustworthy AI Summit, Jan 11, 2023
Trustworthy AI, Nokia Bell Labs, Oct 6, 2022
Practical Approaches to Effectively Manage Transparency (invited talk), Epstein Becker Green's Explainable Artificial Intelligence and Transparency Virtual Briefing, Jun 9, 2022
Defining AI Impact Assessments; Industry Perspectives, Bipartisan Policy Center, May 18, 2022 [video]
Business at OECD (BIAC) Webinar on Trustworthy AI (panelist), Apr 21, 2022
Lessons from IBM on how to create Trustworthy AI (keynote talk), Sony Technical Exchange Fair, Dec 2, 2021
Artificial Intelligence and You podcast interview on AI Explainability, Part 1 (Nov 15, 2021), Part 2 (Nov 22, 2021)
Open Science & Good Research Practice (panel), Third symposium on Biases in Human Computation and Crowdsourcing, November 10, 2021
Measuring with Purpose (panel), NIST AI Measurement and Evaluation Workshop, June 15-17, 2021
AI Governance: Driving Compliance, Efficiency, and Outcomes, Enterprise Data World, April 21, 2021
Trusted AI, University of British Columbia, part of Trustworthy Machine Learning course, April 7, 2021
AI Governance: Driving Compliance, Efficiency, and Outcomes with RBC Bank (keynote), Chief Data & Analytics Officers Financial Services Conference, March 3, 2021 (video)
Race, Tech, and Civil Society: Tools for Combating Bias in Datasets and Models (panel), Stanford Center for Comparative Studies in Race and Ethnicity, February 3, 2021 (video)
What are the roles of explanations throughout the AI life cycle? (panel), NIST Explainabile AI Workshop, January 26-28, 2021.
Increasing Trust and Transparency in AI, Singapore FinTech Festival, December 11, 2020
Trusted AI (invited talk), AI Journey Conference, December 3, 2020
Governance is key to embed AI at scale (panel), Digital Transformation World Series 2020, October 21, 2020
What Are the Research Challenges in Trusted AI? (invited talk), AI and Cybersecurity Issues in Financial Services, September 25, 2020
AI Explainability and Factsheets (interview) in series Trusting AI: Unlocking the Black Box (Episode 3), September 21, 2020
Establishing Trust with AI Ethics and Governance (panel), IBM Data & AI Virtual Forum, July 9, 2020
Increasing Trust in AI (guest lecture), Ethical Implications of AI, Goethe Universtat Frankfurt, June 17, 2020
Trusted AI (talk and panel), IEEE Albany Nanotechnology Symposium, November 12, 2019
Technology and Ethics: Opportunities and Challenges (panel), Law, Justice and Development Week, Washington DC, November 7, 2019
Bringing Trusted AI Research to Society (panel), IBM IT Legal Summit, New York City, October 22, 2019
AI Data and Infrastructure Workshop, National Security Commission on AI, Washington DC, September 18, 2019
Data, Inference & Algorithmic Fairness (talk and panel) at Tech Foundations for Congressional Staff Workshop, Georgetown Law, August 13, 2019
Increasing Trust in AI, (Panel) at Social Justice and Emerging Technologies Conference, CUNY Law School, April 13, 2019
TED: Teaching Explanations for Decisions, Alan Turing Institute, July 27, 2018
Expert Voices Live: An Ethical Approach to Innovation, Axios Roundtable, July 18, 2018
Why isn't the PL/SE Community Working on Cloud Computing?, Institue for Software Research, CMU, October 27, 2015
Changing the Foundation: How the Multicore Era has Impacted Software and What the Future Holds, Invited Course, ACACES'14 summer school, July 13-19, 2014
Changing the Foundation: The Impact of Multicore Architectures on Software SUNY New Paltz School of Science and Engineering Colloquium Series February 14, 2013.
Teaching Programming Language Design and Implementation ... What? To Whom? How?, PLDI'11 Panel, June 8, 2011.
The Impact of Multicore Architectures on Software: Disaster or Opportunity?, Invited Talk, University of Washington, October 20, 2009 (video). Also presented at Tokyo Tech Workshop (keynote), Ghent University, ICT (Beijing), and University of Illinois at Urbana-Champaign (2012).
What Role Does Code Generation and Optimization Play for Multi-Core Enablement? CGO'08 Panel, April 8, 2008.
Dynamic Compilation and Adaptive Optimization in Virtual Machines, Invited Course, ACACES'06 summer school, July 23-29, 2006
Why Software Optimization Matters and Some Thoughts on How to Improve It, Invited Talk, University of Illinois at Urbana-Champaign, April 27, 2005, (Also presented at University of Colorado and Seoul National University)
Virtual Machine Learning: Thinking like a Computer Architect, Keynote, CGO'05, March 21, 2005
The Jikes RVM Story, Invited Talk, Red Hat Free Java Summit, MIT, November 18-19, 2004
Using Jikes RVM to Understand the Hardware Performance of Java Applications, Keynote, MRE'03, March 23, 2003
Pointer Analysis: Haven't We Solved This Problem Yet? Invited Talk, PASTE'01, June 18-19, 2001
Publications
Quantitative AI Risk Assessments: Opportunities and Challenges, Michael Hind, David Piorkowski, John Richards, 2022
Evaluating a Methodology for Increasing AI Transparency: A Case Study, David Piokowski, John Richards, Michael Hind, 2022
A Human-Centered Methodology for Creating AI FactSheets, John Richards, David Piorkowski, Michael Hind, Stephanie Houde, Aleksandra Mojsilovic, and Kush R. Varshney, Bullletin of the Technical Committee on Data Engineering, December, pp. 47-58, 2021
AI Explainability 360: Impact and Design, Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang, 2021
Disparate Impact Diminishes Consumer Trust Even for Advantaged Users, Tim Draws, Zoltan Szlavik, Benjamin Timmermans, Nava Tintarev, Kush R. Varshney and Michael Hind, PERSUASIVE 2021
Best Practices for Insuring AI Algorithms, Phaedra Boinodiris and Michael Hind, Cognitive World, 2020
AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models Vijay Arya, Rachel Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang, Journal of Machine Learning Research (JMLR), Vol 21, 2020
MORE TO COME SOON
Awards, Services, and Other Activities
Tutorials and CourseS
**Program Committees **
2023: FAccT 2023, Big Data 2023
2022: AIES 2022, CHI'22 LBW (reviewer)
2021: AIES 2021
2017: CASCON'17
2016: PLDI'16 EPC, ISMM'16 ERC, ICPP'16
2015: LCPC'15, PLDI'15 ERC
2013: SAC'13 (PL Track)_, _ICPE'13, MUSEPAT'13, CASCON'13
2011: X10 Workshop at PLDI, SAC'11 (PL Track)
2010: ASPLOS'10, PLDI'10 ERC, IWMSE'10, CASCON'10, SAC'10 (PL Track)
2008: IISWC''08, CASCON'08, First Workshop on Programming Language Curricula
2007: WDDD 2007
2004: ISSTA 2004, CC 2004, MRE 2004
2003: OOPSLA'03, Workshop on Exploring the Trace Space for Dynamic Optimization Techniques
2002: 4th Workshop on Binary Translation, JVM'02, ISSTA 2002, ECOOP'02 Workshop on Resource Management for Safe Languages
2001: FDDO'01