Number of training cycles (default = 1). In any cycle either RULES or
PARAMETERS are trained, or both, dependent on
flags setting. This allows f.i. to optimize parameters
after training a machine learning algorithm.
The number of the current training cycle from 1 to NumTrainCycles,
or 0 in [Test] or [Trade]
- When the same parameters are trained several times, each time the start
values are taken from the last optimization cycle
in Ascent mode. This
sometimes improves the result, but requires a longer time for the training process
and increases the likeliness of overfitting. To prevent overfitting, use not more than 2
subsequent parameter optimization cycles.
- The number of optimize calls must not change between
cycles, but optimized parameters can be ignored in particular cycles for special
purposes, and replaced with default parameters.
Example (see also Multitrain.c):
NumTrainCycles = 2; // 2 parameter optimization cycles
TrainMode, NumWFOCycles, NumSampleCycles, NumTotalCycles, NumParameters
► latest version online