Simple and Effective Transfer Learning for Neuro-Symbolic Integration

arXiv:2402.14047v1 Announce Type: new
Abstract: Deep Learning (DL) techniques have achieved remarkable successes in recent years. However, their ability to generalize and execute reasoning tasks remains a challenge. A potential solution to this issue is Neuro-Symbolic Integration (NeSy), where neural approaches are combined with symbolic reasoning. Most of these methods exploit a neural network to map perceptions to symbols and a logical reasoner to predict the output of the downstream task. These methods exhibit superior generalization capacity compared to fully …

abstract arxiv challenge cs.ai cs.lg deep learning exploit integration issue neuro reasoning simple solution symbolic reasoning tasks transfer transfer learning type