0

Machine Learning Logistic Regression

Description: This quiz is designed to assess your understanding of Logistic Regression, a widely used algorithm in Machine Learning for binary classification tasks.
Number of Questions: 15
Created by:
Tags: machine learning logistic regression classification probability
Attempted 0/15 Correct 0 Score 0

Logistic Regression is a type of:

  1. Linear Regression

  2. Polynomial Regression

  3. Classification Algorithm

  4. Clustering Algorithm


Correct Option: C
Explanation:

Logistic Regression is primarily used for binary classification tasks, where the output is predicted as either 0 or 1.

The output of Logistic Regression is:

  1. A continuous value between 0 and 1

  2. A binary value (0 or 1)

  3. A probability value between 0 and 1

  4. A vector of coefficients


Correct Option: C
Explanation:

Logistic Regression produces a probability value between 0 and 1, indicating the likelihood of an observation belonging to a specific class.

The sigmoid function used in Logistic Regression is given by:

  1. $$f(x) = x^2$$

  2. $$f(x) = e^x$$

  3. $$f(x) = 1 / (1 + e^{-x})$$

  4. $$f(x) = x$$


Correct Option: C
Explanation:

The sigmoid function is a crucial component of Logistic Regression, and it maps input values to a probability scale.

The cost function used in Logistic Regression is:

  1. Mean Squared Error (MSE)

  2. Root Mean Squared Error (RMSE)

  3. Cross-Entropy Loss

  4. L1 Regularization


Correct Option: C
Explanation:

Cross-Entropy Loss is commonly used in Logistic Regression to measure the difference between predicted and actual probabilities.

Which regularization technique is commonly used in Logistic Regression to prevent overfitting?

  1. L1 Regularization

  2. L2 Regularization

  3. Dropout

  4. Early Stopping


Correct Option: B
Explanation:

L2 Regularization, also known as Ridge Regression, adds a penalty term to the cost function to discourage large coefficients, thus reducing overfitting.

Logistic Regression is particularly useful when:

  1. The data is linearly separable

  2. The data has a normal distribution

  3. The data is highly imbalanced

  4. The data is categorical


Correct Option: A
Explanation:

Logistic Regression excels when the data is linearly separable, meaning a hyperplane can perfectly separate the two classes.

Which of the following is NOT a hyperparameter in Logistic Regression?

  1. Learning Rate

  2. Regularization Parameter

  3. Number of Epochs

  4. Activation Function


Correct Option: D
Explanation:

Activation Function is not a hyperparameter in Logistic Regression. It is a fixed function, typically the sigmoid function, that transforms the input to a probability.

How can you improve the performance of Logistic Regression when the data is imbalanced?

  1. Use a different classification algorithm

  2. Resample the data

  3. Use a cost-sensitive learning algorithm

  4. Increase the regularization parameter


Correct Option: B
Explanation:

Resampling techniques, such as oversampling or undersampling, can be used to balance the class distribution and improve the performance of Logistic Regression on imbalanced data.

What is the main advantage of Logistic Regression over other classification algorithms?

  1. It is more interpretable

  2. It is more accurate

  3. It is faster to train

  4. It requires less data


Correct Option: A
Explanation:

Logistic Regression is often preferred for its interpretability. The coefficients of the model provide insights into the relationship between features and the target variable.

Which of the following is NOT a common evaluation metric for Logistic Regression?

  1. Accuracy

  2. Precision

  3. Recall

  4. F1 Score


Correct Option: D
Explanation:

F1 Score is not a common evaluation metric specifically for Logistic Regression. It is more commonly used in multi-class classification problems.

Logistic Regression can be extended to handle multi-class classification problems using:

  1. One-vs-All

  2. One-vs-One

  3. Error-Correcting Output Codes

  4. Softmax Regression


Correct Option: D
Explanation:

Softmax Regression is a generalization of Logistic Regression for multi-class classification. It uses a softmax function to convert the output of the model into a probability distribution over multiple classes.

Which of the following is NOT a common application of Logistic Regression?

  1. Predicting customer churn

  2. Detecting fraudulent transactions

  3. Image classification

  4. Natural language processing


Correct Option: C
Explanation:

Image classification is typically handled by more advanced deep learning models, such as Convolutional Neural Networks (CNNs), rather than Logistic Regression.

Logistic Regression is particularly sensitive to:

  1. Outliers

  2. Missing values

  3. Feature scaling

  4. Data imbalance


Correct Option: A
Explanation:

Logistic Regression is sensitive to outliers, as they can significantly influence the model's coefficients and predictions.

To improve the stability and robustness of Logistic Regression, one can:

  1. Use a larger dataset

  2. Regularize the model

  3. Use a different classification algorithm

  4. Increase the number of features


Correct Option: B
Explanation:

Regularization techniques, such as L1 or L2 regularization, can help reduce the impact of outliers and improve the stability of Logistic Regression.

Which of the following is NOT a disadvantage of Logistic Regression?

  1. It can suffer from overfitting

  2. It is sensitive to outliers

  3. It is computationally expensive

  4. It requires a large amount of data


Correct Option: D
Explanation:

Logistic Regression does not necessarily require a large amount of data. It can perform well even with moderate-sized datasets.

- Hide questions