Underfit

What does underfit mean?

Underfitting is the opposite of overfitting. An underfitting models does not seem to perform well on the task you’re training it on. It happens when you have too much data that’s very diverse relative to model’s size.

How to deal with underfitting?

Reduce some data.

You don’t need to use all of your data for training the model.

Increase model size.

Tune the hyper-parameters. Making the model bigger such that it could learn more!