Beginning Anomaly Detection Using

 Optimizers

 SGD

keras.optimizers.SGD()

This is the 

stochastic gradient descent optimizer, a type of algorithm that aids in 

the backpropagation process by adjust the weights. It is commonly used as a training 

algorithm in a variety of machine learning applications, including neural networks.

Appendix A   intro to KerAs

---

346

The optimizer has several parameters:

• 

lr: Some float value where the learning rate lr >= 0. The learning rate 

is a hyperparameter that determines how big of a step to take when 

optimizing the loss function.

• 

momentum: Some float value where the momentum m >= 0. 

This parameter helps accelerate the optimization steps in the 

direction of the optimization, and helps reduce oscillations when 

the local minimum is overshot (refer to Chapter 

3

 to refresh your 

understanding on how a loss function is optimized).

•