IBM Neuro-Symbolic AI Workshop 2022     


IBM Neuro-Symbolic AI Workshop 2022 - overview

IBM Neuro-Symbolic AI Workshop 2022
Unifying Statistical and Symbolic AI


Neuro-symbolic AI combines knowledge-driven symbolic AI and data-driven machine learning approaches.  In this workshop we will show our recent progress toward some of the most outstanding issues in today's AI:

  • Incorporation of complex domain knowledge into learning, including ways to ensure trusted behavior -- and vice versa, incorporation of learning to account for incomplete or imperfect knowledge
  • Rigorous expressive reasoning which is 'soft' (handles uncertainty) while computationally practical
  • Learning with many fewer examples through the use of knowledge
  • Full explainability by construction, including the reasons the models make their decisions
  • Natural language processing via this approach to achieve state-of-the-art results, including handling more complex examples than is possible with today's default AI.

This workshop will include talks from IBM researchers and other academic AI experts. The speakers will share an overview of neuro-symbolic AI technologies, achievements to date, and future direction for the field. The workshop will also include a panel discussion on the future of AI and the possible role of neuro-symbolic AI approaches.

The variety of topics, presentation modalities, and stakeholders will allow the audience of this workshop to reflect on the best path to advance AI in a way that is at the same time scientifically inspiring, economically sustainable, and beneficial to society.


Register to get information about upcoming events. 


Recording of the full workshop is available at LINK



Day 1, Session 1: Introduction -- (Replay)

18 January 2022 (08:30 - 10:40 ET)

Time Topic Speaker
08:30 ET

Workshop Introduction (10 mins)

  • Opening Words
  • Motivation and overview

Lead: Alexander Gray (IBM)

Speakers: Francesca Rossi (IBM), Murray Campbell (IBM), Lior Horesh (IBM)

08:40 ET

Invited talk 1: A Short on the History and Evolution of Neurosymbolic AI (30 mins)

Luis Lamb (Universidade Federal do Rio Grande do Sul)

09:10 ET

Neuro-symbolic AI overview (1 hour + 5 mins QA)

Alexander Gray (IBM)
10:15 ET

General AI and Interactive fiction (30 mins + 5 mins QA)

Murray Campbell (IBM)

Day 1, Session 2: Learnable Reasoning -- (Replay)

18 January 2022 (11:30 - 13:40 ET)

Time Topic Speaker
11:30 ET

Learnable Reasoning (1 hour + 5 mins QA)

Ndivhuwo Makondo (IBM), Hima Karanam (IBM)

12:40 ET

Invited talk 2: Theory of real-valued logics (30 mins)

Ron Fagin (IBM)

13:10 ET

Invited talk 3: Bridging Lukasiewicz logic with Neural Networks: a fruitful link (30 mins)

Antonio di Nola (Università degli Studi di Salerno)

Day 1, Session 3: Natural Language Understanding -- (Replay)

18 January 2022 (14:00 - 16:10 ET)

Time Topic Speaker
14:00 ET

Natural Language Understanding(1 hour + 10 mins QA)

Pavan Kapanipathi (IBM), Salim Roukos (IBM), Radu Florian (IBM)

15:10 ET

Invited talk 4: It’s Time for Reasoning (30 mins)

Dan Roth (University of Pennsylvania & Amazon AWS AI)

15:40 ET

Invited talk 5: System 1 Reasoning with Box Embeddings and System 2 Reasoning from Subgraph Cases (30 mins)

Andrew McCallum (University of Massachusetts Amherst)

Day 1, Session 4: Knowledge Foundations -- (Replay)

18 January 2022 (16:30 - 18:40 ET)

Time Topic Speaker
16:30 ET

Knowledge Foundation (1 hour + 10 mins QA)

Rosario Uceda-Sosa (IBM), Maria Chang (IBM), Guilherme Lima (IBM)

17:40 ET

Invited talk 6: Designing AI-Enabled Systems for Longevity (30 mins)

Deborah L. McGuinness (Rensselaer Polytechnic Institute)

18:10 ET

Invited talk 7: Positive AI with Social Commonsense Models (30 mins)

Maarten Sap (Allen Institute and CMU)



Day 2, Session 1: Optimal Action -- (Replay)

19 January 2022 (08:30 - 10:40 ET)

Time Topic Speaker
08:30 ET

Optimal action (1 hour + 10 mins QA)

Shirin Sohrabi (IBM), Debarun Bhattacharjya (IBM)

09:40 ET

Invited talk 8: Rich Representations for Rational Robots (30 mins)

Leslie Kaelbling (MIT)

10:10 ET

Invited talk 9: Building Taskable Reinforcement Learning Agents (30 mins)

Sheila McIlraith (University of Toronto)

Day 2, Session 2: Insight -- (Replay)

19 January 2022 (11:00 - 13:10 ET)

Time Topic Speaker
11:00 ET

Insight (1 hour + 10 mins QA)

Renato Cerqueira (IBM), Sanjeeb Dash (IBM)

12:10 ET

Invited talk 10: What's new in Learning and Reasoning? (30 mins)

Stephen Muggleton (Imperial College London)

12:40 ET

Invited talk 11: Building machines that see, learn and think like people (30 mins)

Joshua Tenenbaum (MIT)

Day 2, Session 3: Learning with less -- (Replay)

19 January 2022 (13:30 - 15:40 ET)

Time Topic Speaker
13:30 ET

Learning with less (1 hour + 10 mins QA)

Mark Squillante (IBM), Ken Clarkson (IBM)

14:40 ET

Invited talk 12: Meta-Learning (30 mins)

Timothy Hospedales (University of Edinburgh)

15:10 ET

Invited talk 13: Implicit Symbolic Representation and Reasoning in Deep Networks for Vision and Language (30 mins)

Jacob Andreas (MIT)

Day 2, Session 4: Related Advances -- (Replay)

19 January 2022 (16:00 - 18:10 ET)

Time Topic Speaker
16:00 ET

Neuro-symbolic AI related advances (1 hour + 10 mins QA)

Lior Horesh (IBM)

17:10 ET

Invited talk 14: Rebooting AI (30 mins)

Gary Marcus (New York University) 

17:40 ET

Invited talk 15: SynAGI (30 mins)

James Kozloski (IBM)

Day 2, Session 5: Closing -- (Replay)

19 January 2022 (18:15 - 19:30 ET)

Time Topic Speaker
18:15 ET

Neuro-Symbolic AI Toolkit (10 mins + 5 mins QA)

Naweed Khan (IBM)

18:30 ET

Panel: The future of (neuro-symbolic) AI (1 hour)

Moderator: Francesca Rossi (IBM)


19:25 ET

Closing remarks

Alexander Gray (IBM)



If you have any questions feel free to get in touch with the organizer, Asim Munawar at