Search Results for author: Jens U. Kreber

Found 2 papers, 2 papers with code

Generating Symbolic Reasoning Problems with Transformer GANs

1 code implementation19 Oct 2021 Jens U. Kreber, Christopher Hahn

Constructing training data for symbolic reasoning domains is challenging: Existing instances are typically hand-crafted and too few to be trained on directly and synthetically generated instances are often hard to evaluate in terms of their meaningfulness.

Teaching Temporal Logics to Neural Networks

1 code implementation ICLR 2021 Christopher Hahn, Frederik Schmitt, Jens U. Kreber, Markus N. Rabe, Bernd Finkbeiner

We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics.

Cannot find the paper you are looking for? You can Submit a new open access paper.