Quiz

model.add()

model.compile()

model.fit()

model.layers()

Batch size

Optimizer

Number of epochs

Input shape

model.save_weights()

model.to_json()

model.archive()

model.save()

To stop training when a monitored metric stops improving.

To adjust learning rate.

To save the best model only.

To record the training process.

For real-time data augmentation.

For model visualization.

For automatic hyperparameter tuning.

For error logging.

Larger batch sizes require less memory.

Smaller batch sizes typically needs more time for a training step.

Batch size does not affect training.

Larger batch sizes always result in better model performance.

It converts categorical data to numerical data.

It reduces the dimensionality of the data.

It increases the number of features for better model training.

It ensures all features contribute equally to the result.