ann = ANN(math.tanh, tprime, weights, True)
ann.populate(sampled_data)
#Part a
max_itr = 1000
print "Training ANN with no lambda for", max_itr,"iterations"
print "Actual grad, no lambda", ann.calc_err_grad()[0]
print "Numerical grad, no lambda", ann.num_grad()
Eins_a, itr_a = ann.train(max_itr)
print "Finished training"
plot.plot(range(len(Eins_a)), Eins_a, color='r')
plot.savefig("ann-nolamb.png")
plot.clf()
print datetime.datetime.now()
print "Plotting Decision Boundary for ANN with no lambda after", max_itr, "iterations"
ann.decision(savename="ann_nolamb_dec.png")
print datetime.datetime.now()
#-----
lamb = 0.01/len(sampled_data)
ann.reset()
ann.set_weights(weights)
print "Training ANN with lambda", lamb, "for", max_itr, "iterations"
print datetime.datetime.now()
ann.set_lamb(lamb)
print "Actual lambda grad", ann.calc_err_grad()[0]
print "Numerical lambda grad", ann.num_grad()
Eins_b, itr_b = ann.train(max_itr)
print "Finished training"
