| Interface | Description |
|---|---|
| DecayRate |
Many algorithms use a learning rate to adjust the step size by which the
search space is covered.
|
| Class | Description |
|---|---|
| ExponetialDecay |
The Exponential Decay requires the maximum time step to be explicitly known ahead
of time.
|
| InverseDecay |
Decays an input by the inverse of the amount of time that has occurred, the
max time being irrelevant.
|
| LinearDecay |
The Linear Decay requires the maximum time step to be explicitly known ahead
of time.
|
| NoDecay |
A possible value for a decaying learning rate.
|
| PowerDecay |
Decays an input by power of the amount of time that has occurred, the
max time being irrelevant.
|
Copyright © 2017. All rights reserved.