Identity Mappings

[Zipser%cogsci@ucsd.edu]

Geoff,

Perhaps of interest is that in our work with identity mapping of speech, 
the hidden layer spontaneously learned to represent vowels and 
consonants in separate groups of units. Within these groups the 
individual sounds seemed quite compactly coded. 
Maybe the ease with which we are able to identify  
the distinct features used to recognize whole items
depends on the kind of coding they have in our hidden layers.

David Zipser