Productive SRNs

[Javier Marín <jms@um.es>]

Hi all,

I'm trying to set up a trained SRN network (Elman 1990) to be productive. 
That's to say, I want the network form a arbitrary starting input produce 
an output, normalize this output and with a probabilistic algorithm set up 
next input to the network from the normalized output, and continue this for 
a number of cycles.

I am a begginner in PDP++ and although I have tried with Script 
Environments and CSS scripts (based on simple_fsa.css given in demo) 
nothing seems to work. Have anyone done this or something similar?. Is 
there a more specific and complete guide for PDP++ script (many of the 
'simple_fsa.css' functions and objects have no reference in the official 
manual)? Any clue?


Thanks in advance.


Javier

====================================
Dr. Javier Marín Serrano
Dep. Psicología Básica y Metodología
Universidad de Murcia
30100 Campus de Espinardo - Murcia
SPAIN
Tel:  +968 364277
Fax:  +968 364115
====================================