While neural networks have been successfully used in a number of machine learning applications, logical languages have been the standard for the representation of argumentative reasoning. In this paper, we establish a relationship between neural networks and argumentation networks, combining reasoning and learning in the same argumentation framework. We do so by presenting a new neural argumentation algorithm, responsible for translating argumentation networks into standard neural networks. We then show a correspondence between the two networks. The algorithm works not only for acyclic argumentation networks, but also for circular networks, and it enables the accrual of arguments through learning as well as the parallel computation of arguments.
|Number of pages||18|
|Journal||Journal of Logic and Computation|
|State||Published - Dec 2005|
Bibliographical noteFunding Information:
Artur d’Avila Garcez has been partly supported by The Nuffield Foundation. Luis C. Lamb has been partly supported by the Brazilian Research Council CNPq, CAPES, and by the FAPERGS Foundation. We would like to thank the anonymous referees for several supportive comments that led to the improvement of the presentation of this paper.
- Hybrid systems
- Neural-symbolic systems
- Value-based argumentation frameworks