Adam
Bases: Optimizer
Adaptive Moment Estimation (Adam) optimizer.
Combines momentum and adaptive learning rates using moving averages of gradients and squared gradients.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
parameters
|
Trainable model parameters. |
required | |
learning_rate
|
Step size used for parameter updates. |
0.001
|
|
beta1
|
Decay rate for the first moment estimate. |
0.9
|
|
beta2
|
Decay rate for the second moment estimate. |
0.999
|