Explain the difference between L1 and L2 regularization.

What is accuracy and how is it used in model evaluation?

Why is it important to use cross-validation when evaluating a model?

Explain what bias-variance tradeoff is and how it affects model performance.

When should dropout be used as a regularization method?

Compare bagging and boosting. What are their main differences?

How does PCA work and what are its limitations?

When and why should normalization be applied instead of standardization?

What is early stopping and how does it help prevent overfitting?

What is L1 and L2 regularization, and how do they differ?

Explain how the gradient descent algorithm works and what its main variants are.

What is the ReLU activation function, and what are its advantages over the sigmoid function?

When should k-fold cross-validation be used, and what are its advantages?

How does regularization help to reduce overfitting in a model?

Explain the difference between normalization and standardization. When should each method be used?

Explain what boosting is and how it differs from bagging.

What are the main causes of bias and variance in a model?

What is PCA, and how does it help in dimensionality reduction?

How does early stopping work, and when should it be applied?

Explain the difference between normalization and standardization of data.