next up previous
Next: Batch training Up: Initialization Previous: Conjugate Gradient


Rprop ( MSTJN(5) = 15) uses individual learning rates that are dynamically tuned during training according to eq. (gif). It has two learning parameters and two control parameters besides the learning rates (in vector ETAV); the scale factors and ( PARJN(28-29)) and the maximum allowed scale-up and scale-down factors ( PARJN(30-31)). According to [59] the final result is not very sensitive to the choice of the scale factors. Hence the only concern are the initial learning rates, which are set as in the BP case. JETNET uses the value stored in PARJN(1) or ETAL to initialize the learning rates.

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