Question
An ML engineer is training a simple neural network model. The ML engineer tracks the performance of the model over time on a validation dataset. The model's performance improves substantially at first and then degrades after a specific number of epochs.
Which solutions will mitigate this problem? (Choose two.)
- A. Enable early stopping on the model. Correct
- B. Increase dropout in the layers. Correct
- C. Increase the number of layers.
- D. Increase the number of neurons.
- E. Investigate and reduce the sources of model bias.
Explanation
The correct answers are A and B because enabling early stopping (A) can prevent overfitting by halting training when validation performance starts to degrade, while increasing dropout in the layers (B) helps mitigate overfitting by randomly setting a fraction of input units to 0 at each update during training time, which helps reduce co-adaptation on training data.
