MCQsExam.com

What happens if all the neighbors have the same class label in the KNN algorithm?
  1. A-The algorithm assigns the majority class label to the new data point
  2. B-The algorithm assigns the class label of the closest neighbor to the new data point
  3. C-The algorithm assigns a random class label to the new data point
  4. D-The algorithm assigns a weighted class label based on the distance to the neighbors
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the main advantage of the KNN algorithm?
  1. A-Robustness to outliers and noisy data
  2. B-Low computational complexity during training
  3. C-Ability to handle large datasets
  4. D-Interpretability of the model
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the role of cross-validation in tuning the value of K in the KNN algorithm?
  1. A-To select the optimal value of K based on the training data
  2. B-To evaluate the performance of the model on unseen data
  3. C-To reduce the variance of the model
  4. D-To prevent overfitting of the model
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the curse of dimensionality in the context of the KNN algorithm?
  1. A-The increase in computational complexity with higher dimensions
  2. B-The decrease in accuracy with higher dimensions
  3. C-The increase in model flexibility with higher dimensions
  4. D-The decrease in training time with higher dimensions
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the computational complexity of making predictions with the KNN algorithm?
  1. A-O(n)
  2. B-O(log n)
  3. C-O(n log n)
  4. D-O(n^2)
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
How does the choice of distance metric impact the performance of the KNN algorithm?
  1. A-It has no impact on the performance
  2. B-It affects the speed of the algorithm
  3. C-It affects the accuracy of the algorithm
  4. D-It affects the complexity of the decision boundary
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
Which step is NOT involved in the KNN algorithm?
  1. A-Training the model
  2. B-Calculating distances between data points
  3. C-Updating model parameters iteratively
  4. D-Selecting the value of K
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What happens if the value of K is too small in the KNN algorithm?
  1. A-The model becomes more prone to underfitting
  2. B-The model becomes more prone to overfitting
  3. C-The decision boundary becomes smoother
  4. D-The decision boundary becomes more complex
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the main disadvantage of the KNN algorithm?
  1. A-High computational complexity during training
  2. B-Susceptibility to overfitting
  3. C-Sensitivity to outliers and irrelevant features
  4. D-Difficulty in handling high-dimensional data
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
How does the choice of the value of K affect the KNN algorithm?
  1. A-Higher values of K lead to a smoother decision boundary
  2. B-Higher values of K lead to a more complex decision boundary
  3. C-Lower values of K lead to a smoother decision boundary
  4. D-Lower values of K lead to a more complex decision boundary
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
Which distance metric is commonly used in KNN for calculating distances between data points?
  1. A-Euclidean distance
  2. B-Cosine similarity
  3. C-Manhattan distance
  4. D-Minkowski distance
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What does the "K" in KNN represent?
  1. A-Kernel
  2. B-K-means
  3. C-Number of clusters
  4. D-Number of nearest neighbors
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
How does the KNN algorithm make predictions for a new data point?
  1. A-By fitting a decision boundary to the data
  2. B-By calculating the mean of the nearest neighbors' labels
  3. C-By clustering data points into groups
  4. D-By reducing the dimensionality of the data
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the primary objective of the K-Nearest Neighbors (KNN) algorithm in machine learning?
  1. A-Classification
  2. B-Regression
  3. C-Clustering
  4. D-Dimensionality reduction
  5. MCQ By: MCQSEXAM
  6. Data Science / K-Nearest Neighbors (KNN)
  7. More about this MCQ
What is the main advantage of using deep Neural Networks over shallow ones?
  1. A-Lower computational complexity
  2. B-Faster training time
  3. C-Ability to capture complex hierarchical patterns in the data
  4. D-Higher interpretability
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of transfer learning in Neural Networks?
  1. A-Transferring knowledge from one Neural Network to another
  2. B-Transferring pre-trained models to new tasks
  3. C-Transferring data between different layers of a Neural Network
  4. D-Transferring weights between different neurons
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
Which of the following techniques is used to prevent the vanishing gradient problem in deep Neural Networks?
  1. A-Batch normalization
  2. B-Dropout regularization
  3. C-Gradient clipping
  4. D-Early stopping
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of the learning rate in training Neural Networks?
  1. A-Controlling the rate of weight updates during training
  2. B-Controlling the size of the input data
  3. C-Controlling the number of neurons in each layer
  4. D-Controlling the number of training epochs
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the effect of increasing the number of layers in a Neural Network?
  1. A-Decreased model capacity
  2. B-Increased computational complexity
  3. C-Improved generalization performance
  4. D-Decreased risk of overfitting
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of an activation function in a Neural Network?
  1. A-To introduce non-linearity into the model
  2. B-To control the learning rate during training
  3. C-To normalize the input data
  4. D-To regularize the model and prevent overfitting
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
Which of the following is a disadvantage of using deep Neural Networks?
  1. A-Difficulty in interpreting model predictions
  2. B-Prone to underfitting due to model complexity
  3. C-Limited capacity to capture complex patterns in the data
  4. D-Fast training time compared to shallow models
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of pooling layers in a convolutional neural network (CNN)?
  1. A-To reduce the dimensionality of feature maps
  2. B-To increase the spatial resolution of feature maps
  3. C-To introduce non-linearity to the model
  4. D-To regularize the model and prevent overfitting
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is a convolutional neural network (CNN) primarily used for?
  1. A-Natural language processing
  2. B-Image recognition and classification
  3. C-Time series forecasting
  4. D-Reinforcement learning
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is a vanishing gradient problem in Neural Networks?
  1. A-The weights of the model become too large during training
  2. B-The learning rate decreases too rapidly during training
  3. C-The gradients become extremely small, hindering learning in deep networks
  4. D-The model becomes too complex to converge to a solution
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of batch normalization in Neural Networks?
  1. A-Reducing the computational complexity of training
  2. B-Reducing overfitting by adding noise to the input data
  3. C-Normalizing the input data to speed up training
  4. D-Normalizing the activations of intermediate layers to stabilize training
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is overfitting in the context of Neural Networks?
  1. A-The model learns to generalize well to unseen data
  2. B-The model learns to memorize the training data without generalizing
  3. C-The model stops learning before reaching optimal performance
  4. D-The model becomes too simple to capture complex patterns in the data
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
Which of the following is NOT a hyperparameter of a Neural Network?
  1. A-Learning rate
  2. B-Activation function
  3. C-Number of hidden layers
  4. D-Input data
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is dropout regularization in Neural Networks?
  1. A-Dropping out randomly selected neurons during training
  2. B-Reducing the learning rate over time during training
  3. C-Adding noise to the input data during training
  4. D-Applying L1 or L2 regularization to the weights of the model
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the role of backpropagation in training Neural Networks?
  1. A-Adjusting the learning rate during training
  2. B-Propagating errors backward to update the weights
  3. C-Initializing the weights of the Neural Network
  4. D-Regularizing the model to prevent overfitting
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the purpose of the loss function in a Neural Network?
  1. A-Regularizing the model
  2. B-Evaluating the performance of the model
  3. C-Updating the weights of the model
  4. D-Introducing non-linearity to the model
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What does the activation function in a Neural Network do?
  1. A-Computes the output of the Neural Network
  2. B-Computes the loss function of the Neural Network
  3. C-Introduces non-linearity to the model
  4. D-Updates the weights of the Neural Network
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is a perceptron in Neural Networks?
  1. A-A layer in a Neural Network
  2. B-The activation function of a Neural Network
  3. C-The basic building block of a Neural Network
  4. D-The loss function of a Neural Network
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the primary purpose of Neural Networks in machine learning?
  1. A-Clustering
  2. B-Classification and regression
  3. C-Dimensionality reduction
  4. D-Association rule learning
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
Which of the following is NOT a commonly used activation function in Neural Networks?
  1. A-ReLU (Rectified Linear Unit)
  2. B-Sigmoid
  3. C-Tanh (Hyperbolic Tangent)
  4. D-Exponential
  5. MCQ By: MCQSEXAM
  6. Data Science / Neural Networks
  7. More about this MCQ
What is the main advantage of SVM over other classification algorithms?
  1. A-High interpretability
  2. B-Robustness to outliers
  3. C-Low computational cost
  4. D-Ability to handle non-linear relationships
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the kernel function used for in SVM?
  1. A-To transform features into a higher-dimensional space
  2. B-To regularize the model
  3. C-To decrease the number of features
  4. D-To speed up training
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the effect of increasing the regularization parameter C in soft-margin SVM?
  1. A-Larger margin, more misclassifications
  2. B-Smaller margin, fewer misclassifications
  3. C-Larger margin, fewer misclassifications
  4. D-Smaller margin, more misclassifications
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the purpose of the slack variable in soft-margin SVM?
  1. A-To introduce a penalty for misclassifications
  2. B-To increase the margin between classes
  3. C-To decrease the margin between classes
  4. D-To regularize the model
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What does the term "support vector" refer to in SVM?
  1. A-Data points that lie on the decision boundary
  2. B-Data points that are correctly classified
  3. C-Data points that are closest to the decision boundary
  4. D-Data points that are farthest from the decision boundary
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the difference between linear SVM and logistic regression?
  1. A-SVM maximizes the margin between classes, while logistic regression minimizes classification error
  2. B-SVM is a parametric model, while logistic regression is a non-parametric model
  3. C-SVM is a discriminative model, while logistic regression is a generative model
  4. D-SVM is a linear model, while logistic regression is a non-linear model
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the effect of increasing the gamma parameter in an SVM with an RBF kernel?
  1. A-Smoother decision boundary
  2. B-Sharper decision boundary
  3. C-Larger margin
  4. D-Smaller margin
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the kernel trick used for in SVM?
  1. A-To increase the dimensionality of the feature space
  2. B-To decrease the dimensionality of the feature space
  3. C-To transform non-linearly separable data into linearly separable data
  4. D-To regularize the SVM model
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
Which of the following is NOT a commonly used kernel function in SVM?
  1. A-Linear kernel
  2. B-Polynomial kernel
  3. C-Exponential kernel
  4. D-Sigmoid kernel
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the goal of SVM's optimization problem?
  1. A-To maximize the margin between classes
  2. B-To minimize the number of support vectors
  3. C-To minimize the classification error
  4. D-To maximize the sparsity of the solution
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the primary difference between hard-margin and soft-margin SVM?
  1. A-Hard-margin SVM ignores misclassified points, while soft-margin SVM penalizes them
  2. B-Hard-margin SVM allows for misclassification, while soft-margin SVM does not
  3. C-Hard-margin SVM has a larger margin, while soft-margin SVM has a smaller margin
  4. D-Hard-margin SVM uses a linear kernel, while soft-margin SVM uses a non-linear kernel
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the advantage of using a Gaussian (RBF) kernel over a linear kernel in SVM?
  1. A-Gaussian kernel is faster to compute
  2. B-Gaussian kernel handles non-linear relationships between features better
  3. C-Gaussian kernel is less prone to overfitting
  4. D-Gaussian kernel has a higher sparsity level
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the purpose of kernel trick in SVM?
  1. A-To transform non-linearly separable data into linearly separable data
  2. B-To reduce the dimensionality of the feature space
  3. C-To regularize the SVM model
  4. D-To speed up the training process
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the main drawback of SVM when dealing with large datasets?
  1. A-High computational cost
  2. B-Low predictive accuracy
  3. C-Sensitivity to feature scaling
  4. D-Inability to handle non-linear relationships
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
In SVM, what happens if the value of C is very large?
  1. A-The margin is increased
  2. B-The margin is decreased
  3. C-The model becomes more sensitive to outliers
  4. D-The model becomes less sensitive to outliers
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the purpose of regularization parameter C in SVM?
  1. A-To control the width of the margin
  2. B-To control the complexity of the model
  3. C-To control the degree of polynomial kernel
  4. D-To control the influence of misclassified points
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is a support vector in SVM?
  1. A-Data points that are closest to the decision boundary
  2. B-Data points that lie on the decision boundary
  3. C-Data points that are correctly classified
  4. D-Data points that are misclassified
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
Which of the following is NOT a kernel function commonly used in SVM?
  1. A-Linear kernel
  2. B-Polynomial kernel
  3. C-Gaussian kernel
  4. D-Sigmoid kernel
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the primary objective of Support Vector Machines (SVM) in machine learning?
  1. A-Classification
  2. B-Regression
  3. C-Clustering
  4. D-Dimensionality Reduction
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
What is the margin in Support Vector Machine (SVM)?
  1. A-The distance between support vectors
  2. B-The distance between the decision boundary and the support vectors
  3. C-The number of support vectors
  4. D-The width of the decision boundary
  5. MCQ By: MCQSEXAM
  6. Data Science / Support Vector Machines (SVM)
  7. More about this MCQ
Which of the following statements is true about feature importance in Random Forests?
  1. A-Feature importance scores sum up to 1
  2. B-Feature importance scores can be negative
  3. C-Feature importance scores represent the predictive power of features
  4. D-Feature importance scores are not affected by the number of trees in the forest
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the effect of increasing the max_features parameter in Random Forests?
  1. A-Increases model variance
  2. B-Decreases model variance
  3. C-Increases model bias
  4. D-Decreases model bias
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the main difference between bagging and boosting?
  1. A-Bagging trains each model independently, while boosting trains models sequentially
  2. B-Bagging combines multiple weak learners to create a strong learner
  3. C-Bagging reduces variance, while boosting reduces bias
  4. D-Bagging uses random subsets of the data for training
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What happens if the number of trees (n_estimators) in a Random Forest is too high?
  1. A-The model becomes more prone to overfitting
  2. B-The model becomes more prone to underfitting
  3. C-The model becomes more computationally expensive
  4. D-The model's performance remains unaffected
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the recommended approach to tuning hyperparameters in Random Forests?
  1. A-Grid search
  2. B-Random search
  3. C-Manual tuning
  4. D-All of the above
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the purpose of bootstrapping in Random Forests?
  1. A-To reduce the computational complexity of training
  2. B-To increase the number of features used in each tree
  3. C-To reduce bias in the model
  4. D-To create diverse datasets for training each tree
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the main disadvantage of Random Forests compared to decision trees?
  1. A-Random Forests are computationally expensive
  2. B-Random Forests are prone to underfitting
  3. C-Random Forests are less interpretable
  4. D-Random Forests have higher bias
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
In Random Forests, what is the default value of the criterion parameter?
  1. A-"gini"
  2. B-"entropy"
  3. C-"mse"
  4. D-"mae"
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What does the term "random" refer to in Random Forests?
  1. A-Random initialization of parameters
  2. B-Random selection of features
  3. C-Random initialization of weights
  4. D-Random initialization of centroids
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
Which of the following is NOT a hyperparameter of Random Forests?
  1. A-n_estimators
  2. B-max_depth
  3. C-criterion
  4. D-min_samples_split
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the purpose of max_features parameter in Random Forests?
  1. A-It specifies the maximum number of features to consider for splitting at each node
  2. B-It controls the maximum depth of each individual tree
  3. C-It determines the minimum number of samples required to split a node
  4. D-It sets the number of trees in the forest
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
Which of the following is NOT a method to estimate feature importance in Random Forests?
  1. A-Mean decrease in impurity (MDI)
  2. B-Mean decrease in accuracy (MDA)
  3. C-Permutation importance
  4. D-Partial dependence plots
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the purpose of feature importance in Random Forests?
  1. A-To rank features based on their predictive power
  2. B-To increase the number of features used in each tree
  3. C-To reduce the computational complexity of training
  4. D-To remove irrelevant features from the dataset
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is out-of-bag (OOB) error in Random Forests?
  1. A-Error calculated on the training data
  2. B-Error calculated on the validation data
  3. C-Error calculated on data not used during training
  4. D-Error calculated on data not used during testing
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
How does a Random Forest make predictions for classification tasks?
  1. A-By taking the mode of predictions from all trees
  2. B-By taking the mean of predictions from all trees
  3. C-By averaging the probabilities from all trees
  4. D-By summing the predictions from all trees
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the default number of trees in a scikit-learn Random Forest classifier?
  1. A-10
  2. B-50
  3. C-100
  4. D-500
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the purpose of bagging in Random Forests?
  1. A-To reduce bias
  2. B-To reduce variance
  3. C-To speed up training
  4. D-To increase interpretability
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
How does a Random Forest introduce randomness during training?
  1. A-By using a fixed set of features for each tree
  2. B-By training each tree on the entire dataset
  3. C-By selecting a random subset of features for each tree
  4. D-By enforcing a fixed tree depth for each tree
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is a Random Forest composed of?
  1. A-Nodes and branches
  2. B-Features and labels
  3. C-Estimators and trees
  4. D-Leaves and roots
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
What is the primary advantage of Random Forests over a single decision tree?
  1. A-Random Forests are easier to interpret
  2. B-Random Forests are less prone to overfitting
  3. C-Random Forests have faster training time
  4. D-Random Forests require fewer hyperparameters to tune
  5. MCQ By: MCQSEXAM
  6. Data Science / Random Forests
  7. More about this MCQ
How does a decision tree handle missing values during training?
  1. A-It assigns the missing value to the most common value in the dataset
  2. B-It assigns the missing value randomly
  3. C-It uses surrogate splits to handle missing values
  4. D-It removes the samples with missing values from the dataset
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is the maximum depth of a decision tree?
  1. A-The number of nodes in the tree
  2. B-The number of branches in the tree
  3. C-The maximum number of splits from the root node to a leaf node
  4. D-The maximum number of samples in a leaf node
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is a disadvantage of decision trees?
  1. A-Prone to overfitting
  2. B-Require scaling of features
  3. C-Can only handle numerical data
  4. D-Not interpretable
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
Which of the following is NOT a splitting criterion commonly used in decision trees?
  1. A-Gini impurity
  2. B-Information gain
  3. C-Mean squared error
  4. D-Chi-square test
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is entropy in the context of decision trees?
  1. A-A measure of impurity in a set of examples
  2. B-The rate of information gain
  3. C-The number of decision nodes in the tree
  4. D-The depth of the tree
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What does the root node of a decision tree represent?
  1. A-The last decision node
  2. B-The feature that best splits the data
  3. C-The leaf node with the highest information gain
  4. D-The output prediction
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is pruning in the context of decision trees?
  1. A-Trimming branches to reduce model complexity and overfitting
  2. B-Adding more layers to increase model capacity
  3. C-Increasing the depth of the tree to capture more details
  4. D-Removing outliers from the dataset
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
Which algorithm is commonly used to build decision trees?
  1. A-K-means
  2. B-Gradient Descent
  3. C-ID3/C4.5, CART, or Gini impurity
  4. D-Support Vector Machine (SVM)
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is a decision tree composed of?
  1. A-Nodes and branches
  2. B-Features and labels
  3. C-Weights and biases
  4. D-Matrices and vectors
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is the primary objective of Decision Trees in machine learning?
  1. A-Regression
  2. B-Clustering
  3. C-Classification
  4. D-Dimensionality Reduction
  5. MCQ By: MCQSEXAM
  6. Data Science / Decision Trees
  7. More about this MCQ
What is the log-odds ratio in Logistic Regression?
  1. A-The ratio of the probabilities of the two classes
  2. B-The logarithm of the odds of the positive class
  3. C-The logarithm of the odds of the negative class
  4. D-The ratio of the odds of the positive class to the odds of the negative class
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
Which of the following is NOT a method to handle class imbalance in Logistic Regression?
  1. A-Undersampling the majority class
  2. B-Oversampling the minority class
  3. C-Using synthetic minority oversampling technique (SMOTE)
  4. D-Assigning equal weights to each class during training
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What is the purpose of the threshold in Logistic Regression?
  1. A-To determine the learning rate
  2. B-To define the decision boundary between classes
  3. C-To set the number of iterations for training
  4. D-To adjust the sensitivity of the model
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
Which optimization algorithm is commonly used to train Logistic Regression models?
  1. A-Gradient Descent
  2. B-K-means
  3. C-Decision Tree
  4. D-Support Vector Machine (SVM)
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What does the logistic function output for input values outside the range (-∞, +∞)?
  1. A-Values between 0 and 1
  2. B-Values between -1 and 1
  3. C-Values between 0 and ∞
  4. D-Values between -∞ and +∞
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What is the decision boundary in Logistic Regression?
  1. A-The line that separates the data points into two classes
  2. B-The line with the maximum slope
  3. C-The line that minimizes the sum of squared errors
  4. D-The line that intersects the most data points
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
Which of the following evaluation metrics is commonly used for assessing the performance of Logistic Regression models?
  1. A-Mean Squared Error (MSE)
  2. B-R-squared (R2)
  3. C-Accuracy, Precision, Recall, F1-score
  4. D-Area Under the Receiver Operating Characteristic (ROC) Curve (AUC-ROC)
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What type of probability distribution does Logistic Regression assume for the target variable?
  1. A-Gaussian distribution
  2. B-Poisson distribution
  3. C-Binomial distribution
  4. D-Exponential distribution
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
Which activation function is used in Logistic Regression?
  1. A-ReLU
  2. B-Sigmoid
  3. C-Tanh
  4. D-Softmax
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What is the primary objective of Logistic Regression in machine learning?
  1. A-Predicting continuous numerical values
  2. B-Classifying input data into discrete categories
  3. C-Clustering similar data points together
  4. D-Extracting features from raw data
  5. MCQ By: MCQSEXAM
  6. Data Science / Logistic Regression
  7. More about this MCQ
What is the purpose of regularization techniques in Linear Regression?
  1. A-To increase bias and reduce variance
  2. B-To decrease bias and increase variance
  3. C-To penalize large coefficients and reduce overfitting
  4. D-To penalize small coefficients and increase overfitting
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
Which of the following is NOT a method to handle overfitting in Linear Regression?
  1. A-Ridge Regression
  2. B-Lasso Regression
  3. C-Elastic Net Regression
  4. D-Decision Tree Regression
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
What is multicollinearity in the context of Linear Regression?
  1. A-The presence of outliers in the data
  2. B-The relationship between the independent and dependent variables is not linear
  3. C-The presence of strong correlations among independent variables
  4. D-The assumption that the residuals are normally distributed
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
In a simple Linear Regression model with one independent variable, what does the slope coefficient represent?
  1. A-The intercept of the regression line
  2. B-The change in the dependent variable for a one-unit change in the independent variable
  3. C-The average value of the dependent variable
  4. D-The standard deviation of the dependent variable
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
What does the coefficient of determination (R-squared) measure in Linear Regression?
  1. A-The strength of the relationship between independent and dependent variables
  2. B-The slope of the regression line
  3. C-The proportion of variance in the dependent variable explained by the independent variables
  4. D-The intercept of the regression line
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
Which algorithm is commonly used to optimize the parameters in Linear Regression?
  1. A-Gradient Descent
  2. B-K-means
  3. C-Decision Tree
  4. D-Support Vector Machine (SVM)
  5. MCQ By: MCQSEXAM
  6. Data Science / Linear Regression
  7. More about this MCQ
MCQs Exam