MLA-C01 Question 179
Select 3You are training a deep learning model for image classification using a large dataset. During training, you notice that the model performs exceptionally well on the training set but performs poorly on the validation set. Which of the following regularization techniques could help address this issue?
- A
Apply dropout layers during training to randomly deactivate a subset of neurons.
- B
Use L1 regularization to encourage sparsity in the model weights.
- C
Increase the number of layers in the model to improve its capacity.
- D
Apply L2 regularization to reduce the magnitude of the model's weights.
- E
Remove regularization techniques to allow the model to better fit the training data.
Show answer and explanation
Correct answers: A, B, D
Explanation
Overfitting occurs when a model learns to perform well on the training data but fails to generalize to unseen data. Regularization techniques like dropout, L1 regularization, and L2 regularization are effective in combatting overfitting by introducing constraints that prevent the model from becoming overly complex or dependent on specific features of the training data.
- A. Correct.
Dropout is a regularization technique that helps prevent overfitting by randomly deactivating a subset of neurons during training, forcing the model to generalize better.
- B. Correct.
L1 regularization encourages sparsity in the model weights, which can help reduce overfitting by simplifying the model.
- C. Incorrect.
Increasing the number of layers in the model would likely exacerbate overfitting, as it increases the model's capacity to memorize the training data.
- D. Correct.
L2 regularization penalizes large weights in the model, which helps prevent overfitting and improves generalization on unseen data.
- E. Incorrect.
Removing regularization techniques would likely worsen the overfitting issue by allowing the model to memorize the training data even more.