Skip to main content
Research

IBM Neuro-Symbolic AI Summer School

—
  • Virtual
This event has ended.

About

A new era of AI is rapidly emerging: neuro-symbolic AI combines knowledge-driven, symbolic AI with more traditional data-driven machine learning approaches. IBM is a leader in the research and development of neuro-symbolic AI technologies and we invite graduate students, AI practitioners, and anyone interested in this emerging field to participate in the 2022 IBM Neuro-Symbolic AI Summer School, to take place online on August 8-9 of this year.

The Summer School is a follow-on to the IBM Neuro-Symbolic AI Workshop held online in January 2022, which showcased the breadth and depth of the work being done in this field at IBM and by our collaborators. Participation in the first workshop is not a prerequisite for attending this year’s Summer School. All talks in the Summer School are meant to be self-contained.

The key properties of a neuro-symbolic system include:

  • Explainability by construction; the reasons a model makes its decisions should be open to inspection, without the need to do explanatory data analysis;
  • Learning with less and zero-shot learning; the system needs to be able to reason over the domain and over acquired knowledge;
  • Generalization of the solutions to unseen tasks and unforeseen data distributions.

IBM has demonstrated that natural language processing via the neuro-symbolic approach can achieve quantitatively and qualitatively state-of-the-art results, including handling more complex examples than is possible with today’s AI.

This is a virtual event and the registration for the event is free. The registered participants will get access to the recording of all sessions after the event.

Why attend

The summer school will include talks from over 25 IBMers in various areas of theory and the application of neuro-symbolic AI. We will also have a distinguished external speaker to share an overview of neuro-symbolic AI and its history. The agenda is a balance of educational content on neuro-symbolic AI and a discussion of recent results.

Speakers

AG
Artur d'Avila Garcez

Artur d'Avila Garcez

Professor of Computer Science
City University of London
AG
Alexander Gray

Alexander Gray

VP of Foundations of AI
IBM Research
RA
Ramon Astudillo

Ramon Astudillo

Principal Research Scientist
IBM Research
FR
Francesca Rossi

Francesca Rossi

IBM Fellow and AI Ethics Global Leader
IBM Research
MW
Mark Wegman

Mark Wegman

IBM Fellow and Chief Scientist Software Technology
IBM Research
GL
Guilherme Lima

Guilherme Lima

Research Scientist
IBM Research
RF
Ronald Fagin

Ronald Fagin

IBM Fellow
IBM Research
DG
Dinesh Garg

Dinesh Garg

STSM & Manager, Neuro-Symbolic AI & Reasoning
IBM Research

Agenda

  • Opening 20 minutes

    • Welcome (Alexander Gray - IBM)
    • Motivation and Objective (Francesca Rossi - IBM)
    • Summer School Overview (Jon Lenchner - IBM)
    • Neuro-Symbolic AI Essentials Badge (Asim Munawar - IBM)

    Neurosymbolic AI: The Third Wave (Artur d'Avila Garcez - City University of London) 

    FR
    Francesca Rossi
    Francesca Rossi
    IBM Fellow and AI Ethics Global Leader
    IBM Research
    AG
    Alexander Gray
    Alexander Gray
    VP of Foundations of AI
    IBM Research
    JL
    Jon Lenchner
    Jon Lenchner
    Foundations of Computer Science
    IBM Research
    AM
    Asim Munawar
    Asim Munawar
    Program Director for Neuro-Symbolic AI
    IBM Research
    AG
    Artur d'Avila Garcez
    Artur d'Avila Garcez
    Professor of Computer Science
    City University of London

  • Knowledge Foundations for AI Applications (Maria Chang - IBM) 1 hour

    • Knowledge Acquisition and Induction
    • Semantic Web
    • Logic for AI

    IBM Research Overview Part 1: Universal Logic Knowledge Base (Rosario Uceda-Sosa - IBM) 25 minutes

    • Interlinked KBs for broad encyclopedic, linguistic, and commonsense knowledge
    • Supporting foundation for neuro-symbolic reasoning

    IBM Research Overview Part 2: Logic language and hyperknowledge (Guilherme Lima - IBM) 25 minutes

    • Higher order logic and simple type theory
    • The ULKB Logic Language and its Python API

    IBM Research Overview Part 3: Deep linguistic processing (Alexandre Rademaker - IBM) 10 minutes

    • Minimal recursive semantics and abstract meaning representation
    • Open source tooling
    MC
    Maria Chang
    Maria Chang
    Research Staff Member, AI
    IBM Research
    RU
    Rosario Uceda-Sosa
    Rosario Uceda-Sosa
    Researcher, Ontologies, Semantic Models and Services, Inductive Knowledge
    IBM Research
    GL
    Guilherme Lima
    Guilherme Lima
    Research Scientist
    IBM Research
    AR
    Alexandre Rademaker
    Alexandre Rademaker
    Research Scientist
    IBM Research

  • A Very Brief Introduction to Logic and Reasoning (Achille Fokoue-Nkoutche - IBM) 1 hour

    • First order logic (FOL) syntax and model theoretic semantics
    • FOL reasoning and deductive systems
    • FOL Extensions

    Learnable Reasoning (Ndivhuwo Makondo - IBM, Hima Karanam - IBM) 1 hour

    • Overview of Learning to Reason (e.g., neural theorem provers, MLNs, LTNs, etc)
    • Introduction to LNNs - our framework for Learnable Reasoning
    • Applications of LNNS
    AF
    Achille Fokoue-Nkoutche
    Achille Fokoue-Nkoutche
    Research Scientist
    IBM Research
    NM
    Ndivhuwo Makondo
    Ndivhuwo Makondo
    Research Manager
    IBM Research
    HK
    Hima Karanam
    Hima Karanam
    STSM, AI Reasoning
    IBM Research

  • Tutorial: Theory of Reasoning

    • Foundations of Reasoning with Classical Logic (Marco Carmosino - IBM) 30 minutes

      • Desiderata: what is a logic, and what makes a logic "good"?
      • Example: First-Order Logic on finite graphs.
      • Game-based semantics for First-Order Logic

    • Computational Complexity (Jon Lenchner - IBM) 30 minutes

      • Time and Space Complexity: P vs. NP and Related Questions
      • Descriptive Complexity
      • Bridging from Descriptive Complexity to Time and Space Complexity via Games

    IBM Research Overview: Complexity

    • Part I: Theory of Real-Valued Logics (Ron Fagin - IBM) 30 minutes

      • Allowing sentences to take values other than “true” or “false”
      • A rich class of real-valued logic sentences
      • A sound and complete axiomatization

    • Part II: Games and Complexity Classes (Rik Sengupta - IBM) 30 minutes

      • From Ehrenfecht-Fraisse Games to Multi-Structural Games
      • From Multi-Structural Games to Syntactic Games
      • Open Questions
    MC
    Marco Carmosino
    Marco Carmosino
    Research Scientist
    IBM Research
    JL
    Jon Lenchner
    Jon Lenchner
    Foundations of Computer Science
    IBM Research
    RF
    Ronald Fagin
    Ronald Fagin
    IBM Fellow
    IBM Research
    RS
    Rik Sengupta
    Research Intern
    IBM Research