The Complete SPRLIB & ANNLIB

samann_learn_sample: - perform one learning cycles with the SAMANN learning algorithm

SYNOPSIS

int samann_learn_sample

(net, sample1, sample2, eta, alpha, options)

ARGUMENTS

`NET`	*`net`**	Pointer to a net; must be initialised by `samann_init`.
`SAMPLE`	*`sample1`**	A pointer to the first `SAMPLE` used in this cycle.
`SAMPLE`	*`sample2`**	A pointer to the second `SAMPLE` used in this cycle.
`double`	`eta`	The coefficient eta (the learning rate) of the backpropagation rule.
`double`	`alpha`	The coefficient alpha (the momentum term) of the backpropagation rule.
`long`	`options`	See the note below.

RETURNS

TRUE if an error was detected, FALSE if no error was detected.

FUNCTION

First, the distance between sample1 and sample2 in the original dataset is calculated. Then, the network is evaluated twice to find the network output vectors (i.e., the mapping) and calculate the distance between the samples in the map. After the first network evaluation, the samann_adapt_unit function is called to store each UNIT's activation. Then, when the map distance is calculated, samann_adapt_unit is called again to perform the actual weight updates.

NOTE

In the options parameter the following flags are to be specified:

`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.
`SAACCUM`	(Don't) accumulate the delta's.
`SAUPDATE`	(Don't) update the weights.
`SAOLDPRP`	(Don't) backpropagate using the original weights (i.e., the weights as they were before this update of the network).

Note that the HIST-flags and SAMANN-flags may be ORed. Furthermore, note the following for (SAACCUM, SAUPDATE) - 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.

The Complete SPRLIB & ANNLIB

`samann_learn_sample`

- perform one learning cycles with the SAMANN learning algorithm

SYNOPSIS

ARGUMENTS

RETURNS

FUNCTION

NOTE

SEE ALSO

`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.