Abstract
The concept of distribution is often encountered in neural network architectures without any formal quantification. A method of quantifying the amount of distribution present in the hidden layer representations of a feed-forward network with binary inputs is described.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D.J.Chalmers, “Syntactic transformations on distributed representations”, Connection Science, Vol. 2, Nos. 1–2, pp. 53–62, 1990.
L.Chrisman, “Learning recursive distributed representations for holistic computation”, Connection Science, Vol. 3, No. 4, pp. 345–365, 1991.
L.F.Niklasson and N.E.Sharkey, “Connectionism and the issues of compositionality and systematicity”, in R.Trappl (ed) Cybernetics and Systems, Kluwer Academic Publishers: Dordrecht, The Netherlands, 1992.
A.Browne and J.Pilkington, “Unification using a distributed representation”, ACM SIG Bulletin on Artificial Intelligence, Vol. 5, No. 2, pp. 5–7, 1994.
A.Browne and J.Pilkington, “Variable binding in a neural network using a distributed representation,” in M.Verleijsen (ed) Proc. European Symposium on Artificial Neural Networks, pp. 199–204, D. Facto Publications: Brussels, 1994.
A. Browne and J. Pilkington, “Performing structure-sensitive processes on sub-symbolic representations”, Proc. Irish Neural Networks Conference, pp. 19–24, Dublin, 1994.
L.F.Niklasson and M.Boden, “Representing structure and structured representations in connectionist networks”, in A.Browne (ed) Current Perspectives in Neural Computing, Institute of Physics Press: Bristol, UK, 1996 (in press).
M.C.Mozer and P.Smolensky, “Using relevance to reduce network size automatically”, Connection Science, Vol. 1, pp. 3–16, 1989.
T.J.VanGelder, “Defining ‘distributed representation’”, Connection Science, Vol. 4, Nos. 3–4, pp. 175–192, 1992.
N.E.Sharkey, “The ghost of the hybrid: a study of uniquely connectionist representations”, AISB Quarterly, Vol. 79, pp. 10–16, 1992.
J.Pollack, “Recursive distributed representations”, Artificial Intelligence, Vol. 46, pp. 77–105, 1990.
J.L.Elman, “Structured representations and connectionist models”, Proc. 11th Annual Conference of the Cognitive Science Society, pp. 17–25, Lawrence Erlbaum: Hillsdale, NJ, USA, 1989.
R.W.Kentridge, “Neural computation and criticality”, in A.Browne (ed) Current Perspectives in Neural Computing, Institute of Physics Press: Bristol, UK, 1996 (in Press).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Browne, A. Measuring distribution in distributed representations. Neural Process Lett 3, 73–79 (1996). https://doi.org/10.1007/BF00571680
Issue Date:
DOI: https://doi.org/10.1007/BF00571680