MLA-C01 · Question #229
An ML engineer at an entertainment company is refining an ML model to predict audience preferences. As the model learns from data, the ML engineer notices that the model's performance peaks early…
The correct answer is B. Implement early stopping. The described pattern - performance peaks early in training and then gradually declines - is a classic sign of overfitting. The model learns the training data so thoroughly that it starts to lose generalization ability on unseen data. Early stopping addresses this by monitoring…
Question
An ML engineer at an entertainment company is refining an ML model to predict audience preferences. As the model learns from data, the ML engineer notices that the model’s performance peaks early and then begins to gradually decline. The ML engineer must prevent the performance degradation after initial success. Which solution will meet this requirement?
Options
- AIncrease the number of layers.
- BImplement early stopping.
- CAdd more neurons to each layer to capture complex patterns.
- DExamine model bias and variance to understand performance issues.
How the community answered
(25 responses)- B92% (23)
- C4% (1)
- D4% (1)
Explanation
The described pattern - performance peaks early in training and then gradually declines - is a classic sign of overfitting. The model learns the training data so thoroughly that it starts to lose generalization ability on unseen data. Early stopping addresses this by monitoring a validation metric during training and halting the process at the epoch where performance is best, before overfitting degrades the model. Options A and C (more layers, more neurons) increase model capacity, which typically worsens overfitting. Option D (examine bias and variance) is a diagnostic step to understand a problem, not a corrective action - and even then, the symptoms described point clearly to high variance (overfitting), so early stopping is the immediate fix.
Topics
Community Discussion
No community discussion yet for this question.