Exam DP-100 topic 1 question 38 discussion

I would say answer D

Moderator, you should correct the answers, not me! D. You have to add L1/L2 regularization and make use of training data augmentation. Overfitting occurs when a model is too complex for data it is being trained on and memorizes the training data instead of generalizing to new data. To reduce overfitting, you can use regularization techniques such as L1 or L2 regularization, which add a penalty term to the loss function to discourage the model from learning overly complex representations. Additionally, increasing the amount of training data can also help reduce overfitting by giving the model more information to learn from. One common way to increase the amount of training data is to use data augmentation, which involves transforming the existing data in ways that preserve the labels to generate additional training examples.

D is the correct ans

The answer is D. Data augmentation really helps to reduce overfitting and L1L2 are most used regularization in Neural networks.. Dear moderator , please provide the correct answers. Many of them given here is misleading which can make chaos while attending exam

The only option that makes sense to me is D. Adding regularisation will reduce overfitting, similarly adding more data adds more diversity to the training set allowing it to generalise better. So answer is D

ChatGPT answer: Option D: You have to add L1/L2 regularization, and make use of training data augmentation. When a deep CNN model displays hints of overfitting, it means that the model is too complex and has learned to fit the training data too closely. One way to minimize overfitting is to add regularization to the model, which adds a penalty term to the loss function, encouraging the model to choose simpler solutions. L1/L2 regularization adds a penalty term to the loss function that discourages the model from using large weights in the network. This has the effect of reducing the complexity of the model and can help prevent overfitting. Data augmentation is another effective technique to minimize overfitting. It involves applying random transformations to the training data, such as random rotations or translations, to create new training examples that are similar to the original ones. This helps the model to generalize better to unseen data.

Answer is D

Steps for reducing overfitting: Add more data. Use data augmentation. Use architectures that generalize well. Add regularization (mostly dropout, L1/L2 regularization are also possible) Reduce architecture complexity.

D is definitely the answer.

Why don't C?

increse amount of data, simplify the model (decrese layers or NN unit, etc)

I would say D

My vote is for D. A & E discarded because that is increasing the complexity of the architecture. B, C are suggesting reducing the amount of data. D will generate more data for the CNN to be able to generalize more.

Definitely D

I vote for D

Answer is D :)

Answer is D