Signal Prediction Example





Adaptive Linear Layer





Slide 2








 First we must give the network some information about
 the signals.  TIME defines the time steps of this
 simulation.

 >> time = 1:0.01:2.5;

 P defines a signal over these time steps:

 >> X = sin(sin(time).*time*10);
 >> P = con2seq(X);

 T is a signal derived from P by shifting it to the left,
 multiplying it by 2 and adding it to itself:

 >> T = con2seq(2*[0X(1:(end-1))] + X);