정리

• The recommended starting values for your experimentation are between one and a few hundred with 32 often being a good candidate.
• A Larger minibatch size allows computational boosts that utilizes matrix multiplication, in the training.
• In practice, small minibatch sizes have more noise in their error calculations, and this noise is often helpful in preventing the training process from stopping at local minima on the error curve rather than the global minima that creates the best model.