Content and Its Vehicles in Connectionist Systems


  • This paper has been through many incarnations, so I have many people to thank for discussion and comments on earlier versions: Jon Barton, David Chalmers, Paul Churchland, Andy Clark, Martin Davies, Jeff Elman, Justin Fisher, Leonardo Franco, Peter Goldie, Matteo Mameli, David Papineau, Sarah Patterson, Kim Plunkett, Jesse Prinz, Richard Samuels, Paul Schweizer, Gabriel Segal, Helen Steward, Gert Westermann, Michael Wheeler and an anonymous referee for Mind & Language; and audiences in London, Oxford, Edinburgh, at a conference of the European Society for Philosophy and Psychology, at an E.S.R.C. workshop on categorization, and at the Philosophy Program of the Research School of Social Sciences at the Australian National University. The author is grateful to the Arts and Humanities Research Board and the British Academy for their support for this research.

Faculty of Philosophy, University of Oxford; Somerville College, Oxford OX2 6HD, UK.


Abstract:  This paper advocates explicitness about the type of entity to be considered as content-bearing in connectionist systems; it makes a positive proposal about how vehicles of content should be individuated; and it deploys that proposal to argue in favour of representation in connectionist systems. The proposal is that the vehicles of content in some connectionist systems are clusters in the state space of a hidden layer. Attributing content to such vehicles is required to vindicate the standard explanation for some classificatory networks’ ability to generalise to novel samples their correct classification of the samples on which they were trained.