Optimizer

java.lang.Object
- me.yixqiao.jlearn.optimizers.Optimizer

Direct Known Subclasses:

Adam, Momentum, SGD
```
public abstract class Optimizer
extends java.lang.Object
```
Abstract class for optimizers.

Constructor Summary

Constructors
Constructor Description

Optimizer()

Method Summary

All Methods Instance Methods Abstract Methods
Modifier and Type	Method	Description
`abstract Matrix`	`apply(Matrix g)`	Apply the optimizer.
`abstract Optimizer`	`cloneSettings()`	Return a clone of this optimizer's settings.
`abstract void`	`multiplyLR(double d)`	Multiply the learning rate.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - Optimizer
```
public Optimizer()
```
- Method Detail
  - apply
```
public abstract Matrix apply(Matrix g)
```
    Apply the optimizer.
    
    Parameters:
    
    g - errors calculated from backpropagation.
    
    Returns:
    
    the gradients from the optimizer
  - multiplyLR
```
public abstract void multiplyLR(double d)
```
    Multiply the learning rate.
    Used to scale the learning rate in different batch sizes.
    
    Parameters:
    
    d - amount
  - cloneSettings
```
public abstract Optimizer cloneSettings()
```
    Return a clone of this optimizer's settings.
    
    Returns:
    
    the clone