A Feedback Neural Network Model of Causal Learning and Causal Reasoning

Abstract

We present a feedback or recurrent, auto-associative model that captures several important aspects of causal learning and causal reasoning that cannot be handled by feedforward models. First, our model learns asymmetric relations between cause and effect, and can reason in both directions between cause and effect. As a result it can represent an important distinction in causal reasoning, that between necessary and sufficient causes. Second, it predicts cue competition among effects and provides a mechanism for them, something which can only be done with feedforward models by assuming that two separate networks are learned, a highly non parsimonious assumption. Finally, we show that contrary to previous claims, a feedforward model cannot handle Discounting and Augmenting in causal reasoning, although a feedback model can. The success of our feedback model argues for a greater focus on such models of causal learning and reasoning.