What is a key advantage of using cross-validation over a single train-test split for model evaluation?
Correct Answer: C
Explanation:
Cross-validation provides a more robust estimate of model performance by averaging results across multiple folds. This approach reduces the variance in the performance estimate and ensures that the model is evaluated on different subsets of the data, making it more reliable than a single train-test split.
Question 2
Which optimization technique adapts learning rates individually for each parameter?
Correct Answer: C
Explanation:
Adam (Adaptive Moment Estimation) computes adaptive learning rates for each parameter by considering both the first and second moments of the gradient, enhancing convergence speed and performance.
Question 3
In image classification, which technique can be used to prevent the model from memorizing the training data and ensure it generalizes well to new data?
Correct Answer: D
Explanation:
Regularization techniques like Dropout and L2 Regularization help prevent the model from memorizing the training data (overfitting) and ensure it generalizes better to new, unseen data by adding constraints to the learning process.
Demo Practice Mode
You are viewing only the questions marked as Demo.