Skip to main content
U.S. flag

An official website of the United States government

Dot gov

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Https

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explainable AI Workshop

Atop a blue background, the word "explainability" appears.

January 26, 2021 | Explainable AI Workshop
January 27 and January 28, 2021 | Breakout Sessions
January 28, 2021 | Closing Panel

Registration for the Explainable AI workshop is full.

NIST will hold a virtual workshop on Explainable Artificial Intelligence (AI). Explainable AI is a key element of trustworthy AI and there is significant interest in explainable AI from stakeholders, communities, and areas across this multidisciplinary field. As part of NIST’s efforts to provide foundational tools, guidance, and best practices for AI-related research, we released a draft whitepaper, Four Principles of Explainable Artificial Intelligence, for public comment. Inspired by comments received, this workshop will delve further into developing an understanding of explainable AI.

UPDATE:  

For the breakout sessions, all participants who registered for the workshop on January 26, 2021 have been emailed a link to sign up for the breakout sessions.

All workshop participants have also been automatically registered for the Closing Remarks on Thursday January 28, 2021 from 5:00pm–6:00pm ET. A link will be provided closer to the time of the closing remarks.

Please contact explainable-AI@nist.gov if you registered for the workshop and did not receive a breakout session registration link or if you have any questions.

Stay tuned for further announcements and related activity by checking this page or by subscribing to Artificial Intelligence updates through GovDelivery at https://service.govdelivery.com/accounts/USNIST/subscriber/new.

This workshop will consist of plenary speakers, panels, and breakout sessions. Plenary speakers and panels will provide expert insight and a starting point to the discussions. Breakout sessions on Wednesday and Thursday will allow for further facilitated discussions among attendees on the panel topics. All times are Eastern Standard Time.

Day 1: Tuesday January 26, 2021

Time Start

Time End

Topic

11:00 AM

11:30 AM

Welcome to NIST: Charles Romine – ITL Director, NIST

Opening Remarks: Elham Tabassi – ITL Chief of Staff, NIST

11:30 AM

12:00 PM

Overview of Four Principles of Explainable Artificial Intelligence, Draft NISTIR 8312 - P. Jonathon Phillips –  Electronic Engineer, NIST

12:00 PM

1:30 PM

Panel: What are the roles of explanations throughout the AI life cycle?

Moderator:

Amy N. Yates – Mathematician, NIST

Panelists:
Umeshwar Dayal – Corporate Chief Scientist, Senior Fellow: Information Research, Senior Vice President, Hitachi America, Ltd

Michael Hind – Distinguished Research Staff Member, IBM

David Leslie – Ethics Team Lead and Ethics Fellow, the Alan Turing Institute

1:30 PM

2:30 PM

Lunch Break

2:30 PM

4:00 PM

Panel: How does explainable AI fit into the trustworthy AI ecosystem?

Moderator:

Carina Hahn – Social Scientist, NIST

Panelists:
Will Carter – Global Policy Lead for Responsible AI, Google

Sumeet Chabria – Head of Global Business Services, Bank of America 

Frank Torres – Director of Public Policy, Office of Responsible AI, Microsoft 

4:00 PM

4:15 PM

Break

4:15 PM

5:45 PM

Panel: What does a risk management strategy look like for explainable AI?

Moderator:

Peter Fontana – Computer Scientist, NIST

Panelists:
Patrick Hall – Principal Scientist, BNH.AI and George Washington University

Nahla Ivy –  Enterprise Risk Management Officer, NIST

Courtney Lang – Director of Policy, Information Technology Industry Council (ITI)

5:45 PM

6:00 PM

Closing Remarks – Carina Hahn, NIST

Day 2 Breakout Sessions: Wednesday, January 27, 2021

Time Start

Time End

Topic

9:00 AM

10:00 AM

Trustworthy Ecosystem and Explainable AI

10:00 AM

11:00 AM

Break

11:00 AM

12:00 PM

Risk Management and Explainable AI

12:00 PM

1:00 PM

Lunch Break

1:00 PM

2:00 PM

Explanations in AI Life Cycle

2:00 PM

3:00 PM

Break

3:00 PM

4:00 PM

Trustworthy Ecosystem and Explainable AI

4:00 PM

5:00 PM

Break

5:00 PM

6:00 PM

Risk Management and Explainable AI

Day 3 Breakout Sessions and Closing Remarks: Thursday, January 28, 2021

Time Start

Time End

Topic

9:00 AM

10:00 AM

Explanations in AI Life Cycle

10:00 AM

11:00 AM

Break

11:00 AM

12:00 PM

Trustworthy Ecosystem and Explainable AI

12:00 PM

1:00 PM

Lunch Break

1:00 PM

2:00 PM

Risk Management and Explainable AI

2:00 PM

3:00 PM

Break

3:00 PM

4:00 PM

Explanations in AI Life Cycle

4:00 PM

5:00 PM

Break

5:00 PM

6:00 PM

Breakout Debrief

Closing Remarks – Amy N. Yates, NIST

 

Created November 5, 2020, Updated January 22, 2021