Why does the error rise in a SRN?

Gary Cottrell gary at cs.UCSD.EDU
Fri Apr 3 21:12:16 EST 1992


Yes, it seems that Elman nets can't learn in batch mode.
I ported TLEARN to the INTEL hypercube using data parallelism,
and it ran 90 times faster, and learned 90 times slower.

I suspect that all that may be necessary is to go back one more step
in time, but I haven't tried it.

g.



More information about the Connectionists mailing list