Neural-Symbolic Learning and Reasoning: Contributions and Challenges

TLDR

Recent advances in deep neural networks have produced representation learning, but these representations have not yet proven useful for reasoning. The paper aims to integrate robust connectionist learning with sound symbolic reasoning and reviews key contributions and challenges identified at a recent Dagstuhl seminar. The authors conduct a review of neural-symbolic integration contributions and challenges presented at a recent Dagstuhl seminar. Neural‑symbolic computation offers powerful alternatives for knowledge representation, learning, and reasoning in neural computation.

Abstract

The goal of neural-symbolic computation is to integrate robust connectionist learning and sound symbolic reasoning. With the recent advances in connectionist learning, in particular deep neural networks, forms of representation learning have emerged. However, such representations have not become useful for reasoning. Results from neural-symbolic computation have shown to offer powerful alternatives for knowledge representation, learning and reasoning in neural computation. This paper recalls the main contributions and discusses key challenges for neural-symbolic integration which have been identified at a recent Dagstuhl seminar.