next up previous
Next: Conjugate Gradients Up: Choosing the Learning Previous: Quickprop


In a recent benchmark test on a medical data set [59] ``Rprop'' was reported to outperform all other learning algorithms, both in speed and quality. However, its superb performance in this test is related to its use of individual learning rates. Normalizing the data in the way described below makes BP perform as well, if not better [6].

System PRIVILEGED Account
Fri Feb 24 11:28:59 MET 1995