Vassilis Christophides (MIDI research team) is a co-organizer of the “Neuro-Symbolic AI Panel” at the ISWC’23 conference.

The emerging paradigm of neuro-symbolic Artificial Intelligence (AI) stems from the recent efforts to enhance statistical AI (machine learning) with the complementary capabilities of symbolic AI (knowledge and reasoning). In neurosymbolic AI, symbolic knowledge is used to guide deep models, while offering a path toward grounding symbols and inducing knowledge from low-level sensory data. Neuro-symbolic AI aims to demonstrate the capability to (i) solve hard problems requiring cognitive capabilities (ii) learn with significantly fewer data, ultimately for a large number of tasks rather than one narrow task (iii) provide inherently understandable and controllable decisions and actions.

The success stories and the research challenges of neuro-symbolic AI are the main topics of a panel that will take place in Athens, in November 2023 as part of the 22nd International Semantic Web Conference (ISWC).

A few indicative questions for the panel are:

• Which are the foundational problems involved when integrating statistical with symbolic AI?
• In which areas did neurosymbolic AI demonstrate clear benefits?
• What are the opportunities for combining large language models (LLM) with knowledge graphs (KG)?
• How neuro-symbolic techniques relate to other AI paradigms like causal ΑΙ and artificial general intelligence (AGI)?
• What are the common pitfalls in neurosymbolic AI research?