Multi-layer Relation Networks

Preprint English OPEN
Jahrens, Marius; Martinetz, Thomas;
  • Subject: Statistics - Machine Learning | Computer Science - Machine Learning

Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problem... View more
  • References (8)

    [1] Adam Santoro, David Raposo, David G.T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, and Timothy Lillicrap. A simple neural network module for relational reasoning. arXiv:1706.01427, 2017.

    [2] Rasmus Berg Palm, Ulrich Paquet, and Ole Winther. Recurrent Relational Networks for complex relational reasoning. arXiv:1711.08028, 2017.

    [3] Trapit Bansal, Arvind Neelakantan, and Andrew McCallum. RelNet: Endto-End Modeling of Entities & Relations. arXiv:1706.07179, 2017.

    [4] Jihyung Moon, Hyochang Yang, and Sungzoon Cho. Finding ReMO (Related Memory Object): A simple neural architecture for text based reasoning. arXiv:1801.08459, 2018.

    [5] Juan Pavez, and H´ector Allende. Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module. arXiv:1805.09354, 2018.

    [6] Daniel Li, and Asim Kadav. Adaptive Memory Networks. arXiv:1802.00510, 2018.

    [7] Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merri¨enboer, Armand Joulin, and Tomas Mikolov. Towards ai-complete question answering: A set of prerequisite toy tasks. arXiv:1502.05698, 2015.

    [8] David G.T. Barrett, Felix Hill, Adam Santoro, Ari S. Morcos, and Timothy Lillicrap. Measuring abstract reasoning in neural networks. arXiv:1807.04225, 2018.

  • Related Research Results (1)
  • Metrics
Share - Bookmark