The Learning Rate Finder Technique: How Reliable Is It?
Dataiku
JUNE 1, 2020
To understand the evaluation process described in this blog post, we need to take a step back and understand what a hyperparameter in machine learning is. A hyperparameter is a parameter of the model whose value is set before the learning process begins. Finding the optimal values for the hyperparameters of deep models has been long considered “more an art than a science” and relied mainly on trial and error.
Let's personalize your content