Preview

PDF 564Kb

Neural-symbolic systems combine the strengths of neural networks and symbolic formalisms. In this paper, we introduce a neural-symbolic system which combines restricted Boltzmann machines and probabilistic semi-abstract argumentation. We propose to train networks on argument labellings explaining the data, so that any sampled data outcome is associated with an argument labelling. Argument labellings are integrated as constraints within restricted Boltzmann machines, so that the neural networks are used to learn probabilistic dependencies amongst argument labels. Given a dataset and an argumentation graph as prior knowledge, for every example/case K in the dataset, we use a so-called K- maxconsistent labelling of the graph, and an explanation of case K refers to a K-maxconsistent labelling of the given argumentation graph. The abilities of the proposed system to predict correct labellings were evaluated and compared with standard machine learning techniques. Experiments revealed that such argumentation Boltzmann machines can outperform other classification models, especially in noisy settings.

Item Type:	Refereed Conference Paper
Keywords:	neural-symbolic, argumentation, machine learning, reasoning
Research Division:	Information and Computing Sciences
Research Group:	Artificial intelligence
Research Field:	Intelligent robotics
Objective Division:	Law, Politics and Community Services
Objective Group:	Justice and the law
Objective Field:	Legal processes
UTAS Author:	Tran, S (Dr Son Tran)
ID Code:	140695
Year Published:	2020
Deposited By:	Information and Communication Technology
Deposited On:	2020-09-01
Last Modified:	2022-09-06
Downloads:	15 View Download Statistics