neuro Causal and Symbolic AI

Date

Apr 14, 2023, 10:00 am to 12:00 am

Abstract: 

Understanding causal interactions is central to human cognition and thereby a central quest in science, engineering, business, and law. Developmental psychology has shown that children explore the world in a similar way to how scientists do, asking questions such as “What if?” and “Why?” AI research aims to replicate these capabilities in machines. Deep learning in particular has brought about powerful tools for function approximation by means of end-to-end traininable deep neural networks. This capability has been corroborated by tremendous success in countless applications. However, their lack of interpretability and reasoning capabilities prove to be a hindrance towards building systems of human-like ability. Therefore, enabling causal reasoning capabilities in deep learning is of critical importance for research on the path towards human-level intelligence. Also, classical symbolic methods are being revisited and reintegrated into current systems to allow for reasoning capabilities beyond pure pattern recognition. 

This workshop aims to bring together researchers within TAILOR interested in the research areas of neuro-symbolic AI and rigorous formalizations of causality with the goal of developing next-generation AI systems.

Organizing partner: 

TUDA

WP 4 Task: 

Task 4.1

Program : 

10:00 – 10:10 : Devendra Singh Dhami (TU Darmstadt) “Welcome”

Causality

10:10-10:25: Moritz Willig (TU Darmstadt) “Teaching causality to correlational models” 10:25-10:40: Matej Zecevic (TU Darmstadt) “Logic + Causality = Explanations”

 10:40-10:55: Florian Busch (TU Darmstadt) “Computing Counterfactuals using SPNs” 

Neuro- Symbolic

11:00-11:15: Tilman Hinnerichs (TU Delft) “Neuro-symbolic reasoning with ontologies”

11:15-11:30: Arseny Skryagin (TU Darmstadt) “SLASH HAMMER: Handling Avoidance of the Most Matches Evidences Resilience”

11:30-11:45: Issa Hannou (TU Delft) “Neuro-symbolic planning”

11:45-12:00: Hikaru Shindo (TU Darmstadt) “Building Neuro-Symbolic Agents that Can Reason and Act in Visual Scenes”