Probabilistic Reasoning via Deep Learning Neural Association Models

In this paper, we propose a new deep learning approach, called neural association model (NAM), for probabilistic reasoning in artificial intelligence . We propose to use neural networks to model association between any two events in a domain . We take one event as input and compute a conditional probability of the other event to model how likely these two events are to be associated . The actual meaning of the conditional probabilities varies between applications and depends on how the models are trained . Compared with DNNs, RMNNs are superior in knowledge transfer, where a pre-trained model can be quickly extended to an unseen relation after observing only a few training samples . To further prove the effectiveness of the proposed models, in this work, we have applied NAMs to solving challenging Winograd Schema (WS) problems, we’ve applied NIMs to solved NAM’s to solve challenging Wograd Schemma problems. Experiments conducted on a set of WS problems prove that the proposed model has the potential for commonsense reasoning, we say. The proposed models have the potential to be successful in the WS problems have been successful.

Links: PDF - Abstract

Code :


Keywords : model - problems - models - ws - proposed -

Leave a Reply

Your email address will not be published. Required fields are marked *