Hello,
In the first quiz of Structuring Machine Learning course, i’am having trouble to understand 10th question and answer.
Are we allowed to get a training set error first? Should it be only dev or test error to prevent data leakage. Second question is to decrease dev set error, why don’t we get a bigger training set? “Get a bigger training set to reduce variance” choice is wrong. I didn’t understand the reason.
I understood that selecting “try increasing regularization” is not true, this was a mistake but didn’t understand the others.
Thank you
Hi there,
You want your model to perform better on the training data to get closer to the benchmark.
This is why you need to allow the model to learn a more complex behaviour:
- therefore you should try decreasing regularization (and punishing complexity less)
- Train a bigger model (as you selected already)
Reducing variance should not be the problem at the moment since you rather seem to be „underfitting“ than „overfitting“ and want to learn more complexity as stated above. After all your train and dev set error are in a comparable range. Also: feel free to take a look at this article here if you want to take a look at a typical high variance scenario which you rather reach at a („too“) high model complexity: Bias and Variance in Machine Learning - Javatpoint
Best regards
Christian
