T
- the type of the hyperparameterpublic abstract class Hyperparameter<T>
extends java.lang.Object
Some hyperparameters include learning rates, network sizes and shapes, activation choices, and
model selection. In order to evaluate a set of hyperparameters, the only way is to fully train
your model using those choices of hyperparameters. So, the full training loop involves training
the model a number of times using different choices of hyperparameters. This can be mostly
automated by using a HpOptimizer
.
Modifier and Type | Field and Description |
---|---|
protected java.lang.String |
name |
Constructor and Description |
---|
Hyperparameter(java.lang.String name)
Constructs a hyperparameter with the given name.
|
Modifier and Type | Method and Description |
---|---|
java.lang.String |
getName()
Returns the name of the hyperparameter.
|
abstract T |
random()
Returns a random value for the hyperparameter for a range of a fixed value if it is a
HpVal . |
public Hyperparameter(java.lang.String name)
name
- the name of the hyperparameter