Harnessing the Symmetry of Convolutions for Systematic Generalisation

Jeff Mitchell, Jeffrey S Bowers

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

3 Citations (Scopus)
130 Downloads (Pure)


We argue that symmetry is an important consideration in addressing the problem of systematic generalisation and investigate two forms of symmetry relevant to symbolic processes. We implement this approach in terms of convolution and show that it can be used to achieve effective generalisation in a rule learning and a context free language task.

In the rule learning task, we find that symmetry allows us to learn rules that abstract away from the particular symbols that instantiate them, enabling generalisation from seen to unseen symbols. In the language task, symmetry allows us to impose a stack like architecture on the memory cells of a recurrent net, which permits generalisation from simple to more complex structures.
Original languageEnglish
Title of host publicationHarnessing the Symmetry of Convolutions for Systematic Generalisation
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
Publication statusPublished - 24 Jul 2020
EventInternational Joint Conference on Neural Networks 2020 - Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020


ConferenceInternational Joint Conference on Neural Networks 2020
Abbreviated titleIJCNN 2020
Country/TerritoryUnited Kingdom
Internet address

Structured keywords

  • Brain and Behaviour


  • connectionism and neural nets
  • symbolic and algebraic manipulation
  • convolution


Dive into the research topics of 'Harnessing the Symmetry of Convolutions for Systematic Generalisation'. Together they form a unique fingerprint.
  • M and M

    Bowers, J. S.


    Project: Research, Parent

Cite this