Narrow Results

In this work, we develop a neural model to solve causal reasoning problems (said also abduction) in the open, independent and incompatibility classes. We model the reasoning process by a single and global energy function using cooperative and competitive neural computation. The update rules of the distinct connections of the network are derived from its energy function using gradient descent techniques. Simulation results reveal a good performance of the model.

In the last decade, abduction has been a very active research area. This results in a variety of models mechanizing abduction, namely within a probablistic or logical framework. Recently, a few abductive models have been proposed within a neural framework. Unfortunately, these neural-/probablistic-/logical-based models focus on the most simple class, called independent abduction problems. In this paper, we propose a neural-based model to deal with incompatibility abduction problems. To our knowledge, our model is the first one able to efficiently generate best explanations to the complex class of incompatibility abduction problems.

Causal reasoning is a hard task that cognitive agents perform reliably and quickly. A particular class of causal reasoning that raises several difficulties is the cancellation class. Cancellation occurs when a set of causes (hypotheses) cancel each other's explanation with respect to a given effect (observation). For example, a cloudy sky may suggest a rainy weather; whereas a shiny sky may suggest the absence of rain. In this work we extend a recent neural model to handle cancellation interactions. Simulation results are very satisfactory and should encourage research.