AWS Certified Machine Learning Engineer – Associate (MLA-C01) — Question 18

An ML engineer has trained a neural network by using stochastic gradient descent (SGD). The neural network performs poorly on the test set. The values for training loss and validation loss remain high and show an oscillating pattern. The values decrease for a few epochs and then increase for a few epochs before repeating the same cycle.
What should the ML engineer do to improve the training process?

Answer options

• A. Introduce early stopping.
• B. Increase the size of the test set.
• C. Increase the learning rate.
• D. Decrease the learning rate.

Correct answer: D

Explanation

The correct answer is D because a high learning rate can cause the model to oscillate and not converge properly, leading to poor performance. Lowering the learning rate allows for more stable and gradual updates to the model weights, which can help reduce oscillation and improve convergence. Options A and B do not directly address the oscillation issue, and option C would likely exacerbate the problem instead of solving it.