NEURAL-SYMBOLIC LEARNING AND REASONING ASSOCIATION
(NeSy AI)
RESEARCH ON NEUROSYMBOLIC AI
About The NeSy Association
NeSy is about the integration of neural and symbolic AI, combining the statistical nature of machine learning with knowledge representation and reasoning. Deep learning has achieved industrial relevance in a number of areas from healthcare to finance and business, obtaining state-of-the-art performance on language modelling, speech and image recognition, sensor data and graph analytics. Symbolic AI is challenged by such unstructured large data, but offers sound and well-understood formal reasoning with explanations via knowledge representation and agentic AI that can be inspected to interpret and validate how decisions follow from data. Neural and symbolic AI also contrast in the problems that they excel at. Deep learning excels at multimodal learning and scene recognition, but fails at planning and rich causal and deductive reasoning.
Neurosymbolic AI aims to build rich computational AI models, systems and applications by combining neural and symbolic learning and reasoning. It seeks to complement the strengths of deep neural networks and symbolic AI while overcoming their respective weaknesses, addressing urgent issues of data efficiency, fairness, trust and safety of AI. The NeSy conference series is the premier venue for the presentation and discussion of the theory and practice of neurosymbolic AI. Since the first NeSy in 2005, the series provided an atmosphere for the free exchange of ideas, bringing together the community of scientists and practitioners that straddle the line between connectionism and symbolic AI.
How it began...
At Dagstuhl seminar 14381, Wadern, Germany, marking the tenth edition of the workshop on Neural-Symbolic Learning and Reasoning, September 2014, it was decided that Neural-Symbolic Learning and Reasoning should become an Association (NeSy AI) with a charter and a more formal membership and governance structure.
The object of the NeSy AI association is to promote research in neurosymbolic AI, the integration of learning and reasoning, communication and exchange of best practice among associated research areas. As such, the NeSy association primarily conducts the annual conference on Neurosymbolic Learning and Reasoning (NeSy), and promotes through the maintenance of this website and its management board, which acts as the steering committee for the NeSy conference series, interactions with related associations such as IFCoLog, INNS, BCS, IEEE, ACM, AAAI, CogSci, NeurIPS.
With the creation of the NeSy conference, the Neurosymbolic AI journal and the expansion of the NeSy community, the NeSy association is being updated to address the needs of an expanding community and activities with a new management board and advisory board.
We invite every researcher and practitioner interested in the object of the NeSy association to join our mailing list and community slack.
With best regards,
The NeSy Association Board
NeSy Association Board:
Artur d'Avila Garcez (president)
Pascal Hitzler (vice-president)
Tarek Besold
Ernesto Jimenez-Ruiz
Leilani Gilpin
NeSy Advisory Board:
Kai-Uwe Kühnberger, Luis C. Lamb, Luc de Raedt, Daniel Silver, Leslie Valiant, Marco Gori, Francesca Rossi, Kristian Kersting.