int pn_learn | (net, data_set, eta, alpha, mu, cycles, options) |
NET | *net | Pointer to a net; must be initialized by pn_init. |
DATASET | *dset | A pointer to a learning set (must be an IOSET). |
double | eta | The coefficient eta (the learning rate) of the backpropagation rule. |
double | alpha | The coefficient alpha (the momentum term) of the backpropagation rule. |
double | mu | A small constant used in diverting inflection points in the pseudo-Newton method. |
long | cycles | Number of learning cycles to be performed. |
long | options | See the note below. |
HISTU | (Don't) store history of unit values at each update. |
HISTT | (Don't) store history of unit thetas at each update. |
HISTW | (Don't) store history of weights at each update. |
BPACCUM | (Don't) accumulate the delta's. |
BPUPDATE | (Don't) update the weights. |
BPBATCH | (Don't) perform batch-updating backpropagation (i.e. update the weights after the last sample). |
Note that the HIST-flags and BP-flags may be ORed together. Furthermore, note the following for (BPBATCH, BPACCUM, BPUPDATE) triples:
0 | 0 | 0: Combination does not make sense (nothing is done). |
0 | 0 | 1: Yields no backpropagation, only updates. |
0 | 1 | 0: Yields only backpropagation, no updates. |
0 | 1 | 1: Specifies normal mode, i.e. backpropagation and update. |
1 | 0 | 0: Combination does not make sense (nothing is done). |
1 | 0 | 1: Error: impossible combination. |
1 | 1 | 0: Specifies normal batch mode. |
1 | 1 | 1: Error: impossible combination. |
Finally, note that this function use the store_hist_all_units, store_hist_all_weights and store_hist_all_thetas functions.
This document was generated using api2html on Thu Mar 5 09:00:00 MET DST 1998