Fine-Tuning Models
Learn fine-tuning techniques to improve a model’s performance.
We'll cover the following
Underfitting & overfitting
Underfitting refers to the model’s failure to learn. Somehow, the model can’t improve itself, and we see that training and validation accuracy get stuck without getting any better with further iterations. A primary reason for this is to have vanishing or exploding gradients. As we mentioned, both problems are about having bad values to update weights, which causes the learning to stop.
Note: The figures below show us what happens if we set
LEARNING_RATE = 1.0
.
Get hands-on with 1200+ tech skills courses.