Amazon
MLS-C01 · Question #13
A Machine Learning Specialist built an image classification deep learning model. However, the Specialist ran into an overfitting problem in which the training and testing accuracies were 99% and…
The correct answer is B. The dropout rate at the flatten layer should be increased because the model is not generalized. https://kharshit.github.io/blog/2018/05/04/dropout-prevent-overfitting
Modeling
Question
A Machine Learning Specialist built an image classification deep learning model. However, the Specialist ran into an overfitting problem in which the training and testing accuracies were 99% and 75%, respectively. How should the Specialist address this issue and what is the reason behind it?
Options
- AThe learning rate should be increased because the optimization process was trapped at a local
- BThe dropout rate at the flatten layer should be increased because the model is not generalized
- CThe dimensionality of dense layer next to the flatten layer should be increased because the model
- DThe epoch number should be increased because the optimization process was terminated before
How the community answered
(48 responses)- A8% (4)
- B85% (41)
- C2% (1)
- D4% (2)
Explanation
https://kharshit.github.io/blog/2018/05/04/dropout-prevent-overfitting
Topics
#Overfitting#Dropout#Neural Networks#Regularization
Community Discussion
No community discussion yet for this question.