ECAI 2004 Conference Paper

[PDF] [full paper] [prev] [tofc] [next]

Argumentation Neural Networks: Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems

Artur d'Avila Garcez, Luis C. Lamb, Dov M. Gabbay

While neural networks have been successfully used in a number of machine learning applications, logical languages have been the standard for the representation of legal and argumentative reasoning. In this paper, we present a new hybrid model of computation that allows for the deduction and learning of argumentative reasoning. We do so by using Neural-Symbolic Learning Systems where non-classical reasoning is representable. We propose a Neural Argumentation Algorithm to translate argumentation networks into standard neural networks. We then show a correspondence between the semantics of the two networks. The algorithm works not only for acyclic argumentation networks but also for circular networks. The approach enables cummulative argumentation through learning, as the strength of the arguments change over time.

Keywords: Neural-Symbolic Systems, Value-based Argumentation Frameworks, Hybrid Systems, Argumentation

Citation: Artur d'Avila Garcez, Luis C. Lamb, Dov M. Gabbay: Argumentation Neural Networks: Value-based Argumentation Frameworks as Neural-Symbolic Learning Systems . In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.987-988.


[prev] [tofc] [next]


ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).