0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Learning Invariants through Soft Unification

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Human reasoning involves recognising common underlying principles across many examples by utilising variables. The by-products of such reasoning are invariants that capture patterns across examples such as "if someone went somewhere then they are there" without mentioning specific people or places. Humans learn what variables are and how to use them at a young age, and the question this paper addresses is whether machines can also learn and use variables solely from examples without requiring human pre-engineering. We propose Unification Networks that incorporate soft unification into neural networks to learn variables and by doing so lift examples into invariants that can then be used to solve a given task. We evaluate our approach on four datasets to demonstrate that learning invariants captures patterns in the data and can improve performance over baselines.

          Related collections

          Most cited references14

          • Record: found
          • Abstract: not found
          • Article: not found

          Hybrid computing using a neural network with dynamic external memory

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              The mythos of model interpretability

                Bookmark

                Author and article information

                Journal
                16 September 2019
                Article
                1909.07328
                cf70f869-b3b9-405d-9104-4d8bfbeeeb05

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                Preprint, work in progress
                cs.LG cs.AI stat.ML

                Machine learning,Artificial intelligence
                Machine learning, Artificial intelligence

                Comments

                Comment on this article