Non linear Regression: Why isn't the model learning?

Question

I just started learning keras. I am trying to train a non-linear regression model in keras but model doesn\'t seem to learn much.

Answer 1

Your learning rate is way too high.

Also, irrelevant to your issue, but you should not ask for metrics=['accuracy'], as this is a regression setting and accuracy is meaningless.

So, with these changes:

sgd = SGD(lr=0.001);
model.compile(loss='mse', optimizer=sgd)

plt.legend([ 'Predicted Y' ,'Actual Y']) # typo in legend :)

here are some outputs (results will be different among runs, due to the random element of your y):