How a neural net grows symbols

In Peter Bartlett (ed.), Proceedings of the Seventh Australian Conference on Neural Networks, Canberra. Canberra, Australia: ACNN '96. pp. 91-96 (1996)
  Copy   BIBTEX


Brains, unlike artificial neural nets, use symbols to summarise and reason about perceptual input. But unlike symbolic AI, they “ground” the symbols in the data: the symbols have meaning in terms of data, not just meaning imposed by the outside user. If neural nets could be made to grow their own symbols in the way that brains do, there would be a good prospect of combining neural networks and symbolic AI, in such a way as to combine the good features of each. The article argues the cluster analysis provides algorithms to perform the task, and that any solution to the task must be a form of cluster analysis

Author's Profile

James Franklin
University of New South Wales


Added to PP

88 (#63,775)

6 months
11 (#75,085)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?