MLS-C01 Modeling Practice Question

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✓

  Increase the batch size used during training.

  Why this is correct

  Increasing the batch size allows the model to process more samples per gradient update, reducing the number of iterations per epoch and thus speeding up training. This is a common technique to reduce training time without changing the algorithm or hardware.

• ✗

  Add regularization to the loss function.

  Why it's wrong here

  Adding regularization (e.g., L1/L2 penalties) introduces extra computation and does not reduce training time; it may even increase it slightly. It is used to prevent overfitting, not to speed up training.

• ✗

  Use data augmentation to increase the dataset size.

  Why it's wrong here

  Data augmentation increases the dataset size by creating modified copies of existing data, which increases the number of samples to train on, thereby increasing training time.

• ✗

  Reduce the number of training epochs.

  Why it's wrong here

  Reducing the number of epochs also reduces training time, but it decreases the number of times the model sees the data, which can significantly harm model performance (underfitting). While it would reduce time, it is less desirable than increasing batch size because it directly sacrifices learning.