Exam AWS Certified Machine Learning - Specialty topic 1 question 232 discussion

A: possible but unlikely for movie reviews B: wrong https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&cad=rja&uact=8&ved=2ahUKEwi31N_10eX9AhWYQ0EAHXDFCAwQFnoECA8QAw&url=https%3A%2F%2Fdeepchecks.com%2Fquestion%2Fdoes-learning-rate-affect-overfitting%2F&usg=AOvVaw19RT-u_XyEe8FG_10R6aFC C: wrong because would increase complexity and potentially overfitting D: correct E: correct F: correct

Overfitting solutions must be regularization, dropout and adjusting learning rate. F is wrong, decreasing number of layers is not the top recommendations to solve overfitting, it may even cause underfitting.

A. NO B. NO - decreasing the learning rate make may increase accuracy thus increase overfitting C. NO - more complexity tend to increase overfitting D. YES - best practice E. YES - best practice, will reduce model complexity and thus increase generalization F. YES - best practice, will reduce model complexity and thus increase generalization

d and E for sure. i am a bit confused F and B

To improve the generalization of the deep learning sentiment analysis model and reduce overfitting, the following three solutions can be implemented: Add Dropout: Dropout is a regularization technique that randomly drops out (sets to zero) a certain percentage of nodes in the neural network during each training epoch. This helps to prevent overfitting and improve generalization. Add L1 and L2 Regularization: L1 and L2 regularization are techniques used to add a penalty to the loss function of the neural network, which helps to prevent overfitting. L1 regularization adds a penalty based on the absolute value of the weights, while L2 regularization adds a penalty based on the squared value of the weights. Decrease the number of layers in the network: Deep neural networks with too many layers can be prone to overfitting. Reducing the number of layers in the network can help to prevent overfitting and improve generalization.

We don't have to touch learning rate because the model is overfitting

DEF are correct