Question on BP..

[Scott.Fahlman@B.GP.CS.CMU.EDU]

    	I would like to know if continous valued inputs can be used 
    	for the Back Propagation algorithm ?    

Yes, definitely.  For two good examples, see the work of Lapedes and Farber
at Los Alamos on predicting time series (I don't have the reference handy)
and the work on the two-spirals benchmark.  The latter is described in a
paper by Lang & Witbrock in the Proceedings of the 1988 Connectionist
Models Summer School and in follow-up work presented by me and Chris
Lebiere in the 1989 NIPS conference (proceedings due out in April or so,
tech report sooner).  In addition, most of the problems I've seen on
phoneme labeling and sonar use multiple continuous-valued inputs.

-- Scott Fahlman