Before applying our multilayer perceptron to understand fluctuations in the currency market exchanges, let's get acquainted with some of the key learning parameters introduced in the first section.
The purpose of the first exercise is to evaluate the impact of the learning rate, , on the convergence of the training epoch, as measured by the sum of the squared errors of all output variables. The observations
x (with respect to the labeled output,
y) are synthetically generated using several noisy patterns: functions
noise, as follows:
val noise = () => NOISE_RATIO*Random.nextDouble val f1 = (x: Double) ...