Deep Learning Quiz

What is L2 regularization also known as?

• Ridge Regression

• Lasso Regression

• Elastic Net

• Decision Trees

What is Grid Search?

• An algorithm for feature selection.

• A method for exploring a range of hyperparameter combinations.

• A method for data normalization.

• A type of neural network architecture.

What does the ROC curve represent?

• Trade-off between sensitivity and specificity.

• Trade-off between precision and recall.

• Trade-off between false positive rate and true positive rate.

• Trade-off between accuracy and error rate.

Which optimization algorithm is most commonly used in deep learning?

• K-Means

• Stochastic Gradient Descent (SGD)

• Principal Component Analysis (PCA)

• Linear Regression

What is accuracy in the context of classification models?

• The ratio of correctly predicted instances to the total instances.

• The ratio of true positives to the total positive predictions.

• The ratio of true positives to the total actual positives.

• The ratio of false positives to the total predictions.

What is transfer learning?

• Training a model from scratch on a new dataset.

• Using a pre-trained model on a new but related task.

• Combining multiple models into an ensemble.

• Using unlabeled data for training.

What does one-hot encoding do?

• Converts categorical variables into binary vectors.

• Normalizes numerical data.

• Removes missing values.

• Reduces dimensionality.

Which method is commonly used for hyperparameter tuning?

• Backpropagation

• Cross-Validation

• Gradient Descent

• Dropout

What is a learning rate?

• The rate at which data is fed into the model.

• The rate at which the loss function decreases.

• The size of the steps taken during gradient descent.

• The rate of change in model architecture.

What is batch normalization used for?

• Normalizing the output layer.

• Normalizing the input layer.

• Normalizing the activations of each layer.

• Normalizing the loss function.