I was adapting the next demo code to my own needs The demo I used to "learn". I want to change the demo code in order to study the next simple model.
def model(c,I,t):
return I*np.exp(-c*t)
I want to fit/adjust a GP regressor to the next target function:
def my_target(t):
return model(0.2,5,t)
The ranges of variations of the parameters are given in the next dictionary:
pbounds = {'c': (0, 0.4), 'I': (8, 10), 't':(0,10)}
The gaussian process regression is instanciated in the next object
bo = BayesianOptimization(model,pbounds,verbose=2,random_state=1)
How does bo received information to fit to target???...
From the demo the gaussian process adjustments are done calling the method
bo.maximize(init_points=0, n_iter=5, kappa=5).
Once again how did the function was connected to my target????
I am trying to reproduce this example my benchmark case employing GPs....
Thanks.
