Answer-first summary for fast verification
Answer: Run a hyperparameter tuning job on AI Platform to optimize for the L2 regularization and dropout parameters.
To make the model more resilient to overfitting, the best approach is to use regularization techniques and optimize their parameters. In this context, running a hyperparameter tuning job on AI Platform to find the optimal values for L2 regularization and dropout parameters (option C) is most effective. This approach allows the system to automatically determine the best settings to reduce overfitting. Options A and B suggest specific but arbitrary values which may not be optimal for your model. Option D, increasing the number of neurons, could actually exacerbate overfitting, making it a less suitable choice.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
After training a deep neural network model on Google Cloud, you observe that the model exhibits low loss on the training data but performs poorly on the validation data, indicating overfitting. To make the model more resilient to overfitting, which strategy should you use when retraining the model?
A
Apply a dropout parameter of 0.2, and decrease the learning rate by a factor of 10.
B
Apply a L2 regularization parameter of 0.4, and decrease the learning rate by a factor of 10.
C
Run a hyperparameter tuning job on AI Platform to optimize for the L2 regularization and dropout parameters.
D
Run a hyperparameter tuning job on AI Platform to optimize for the learning rate, and increase the number of neurons by a factor of 2.
No comments yet.