Hard Competitive Learning

5.4.2

Variable

Switches from a constant to a variable learning rate.

epsilon

This value ($\epsilon$) determines the extent to which the winner is adapted towards the input signal (constant learning rate).

epsilon_i

epsilon initial ($\epsilon_i$).

epsilon_f

epsilon final ($\epsilon_f$).

t_max

The simulation ends, if the number of input signals exceeds this value (t_max).

The variable learning rate is determined according to

$$\qquad\epsilon(t) = \epsilon_i(\epsilon_f/\epsilon_i)^{t/t_{\rm max}}.$$