I fail to see the point, even in general (i.e., c, or c++); most
neural net models have limit solutions, meaning that one can simply
solve the math; no iterative solution is needed. In that case,
transcript is just fine (well, it would be improved with engine-based
SVD and eigenvector extraction routines, but I quibble).
--
Please avoid sending me Word or PowerPoint attachments.
See <http://www.gnu.org/philosophy/no-word-attachments.html>
-Dr. John R. Vokey
_______________________________________________
use-revolution mailing list
[email protected]
Please visit this url to subscribe, unsubscribe and manage your subscription
preferences:
http://lists.runrev.com/mailman/listinfo/use-revolution
