Hands on Machine Learning CH3, CH4

Which of the following is the correct definition of a support vector machine (SVM)? a) A machine learning algorithm that finds the best hyperplane that separates two classes of data points b) A machine learning algorithm that finds the best line that separates two classes of data points c) A machine learning algorithm that finds the best curve that separates two classes of data points d) A machine learning algorithm that finds the best surface that separates two classes of data points

a) A machine learning algorithm that finds the best hyperplane that separates two classes of data points

What are the advantages and disadvantages of using a logistic regression algorithm for classification?

Can handle both linear and non-linear data Robust to noise in the data Can be used for both classification and regression task Disadvantages: Can be computationally expensive to train Difficult to interpret the results

What are the advantages and disadvantages of using a random forest algorithm for classification?

Can handle both linear and non-linear data Robust to noise in the data Can be used for both classification and regression tasks Easy to interpret the results Disadvantages: Can be computationally expensive to train Can be difficult to tune the hyperparameters

Which of the following is NOT an advantage of using a decision tree for classification? a) Easy to understand and interpret b) Can handle both categorical and numerical features c) Can be used for both classification and regression tasks d) Can handle non-linear data

Can handle non-linear data

Which of the following is NOT an advantage of using a k-nearest neighbors algorithm for classification? a) Simple to understand and implement b) Can handle both categorical and numerical features c) Can be used for both classification and regression tasks d) Can handle non-linear data

Can handle non-linear data

Which of the following is NOT a disadvantage of using a gradient boosting algorithm for classification? a) Can be computationally expensive to train b) Can be difficult to tune the hyperparameters c) Can only handle linear data d) Robust to noise in the data

Can only handle linear data

Which of the following is NOT a disadvantage of using a random forest algorithm for classification? a) Can be computationally expensive to train b) Can be difficult to tune the hyperparameters c) Can only handle linear data d) Easy to interpret the results

Can only handle linear data

Which of the following is NOT a disadvantage of using a support vector machine for classification? a) Can be computationally expensive to train b) Difficult to interpret the results c) Can only handle linear data d) Robust to noise in the data

Can only handle linear data

Which of the following is NOT a type of unsupervised learning algorithm? a) Clustering b) Dimensionality reduction c) Anomaly detection d) Classification

Classification

Which of the following is NOT a type of supervised learning algorithm? a) Classification b) Regression c) Clustering d) Anomaly detection

Clustering

What are the different types of unsupervised learning algorithms?

Clustering algorithms, which group similar data points together. Dimensionality reduction algorithms, which reduce the number of features in a dataset. Anomaly detection algorithms, which identify data points that are significantly different from the rest of the data.

What is the process of cross-validation and how is it used to evaluate the performance of a machine learning model?

Cross-validation is a technique used to evaluate the performance of a machine learning model on unseen data. It involves splitting the data into multiple subsets, training the model on each subset, and then evaluating the performance of the model on the remaining data. The average performance over all of the subsets is used as the final evaluation of the model.

What are the different types of classification algorithms?

Decision trees Support vector machines k-nearest neighbors Naive Bayes Random forest

Which of the following is NOT an advantage of using a logistic regression algorithm for classification? a) Can handle both linear and non-linear data b) Robust to noise in the data c) Can be used for both classification and regression tasks d) Easy to interpret the results

Easy to interpret the results

What are the advantages and disadvantages of using a decision tree for classification?

Easy to understand and interpret Can handle both categorical and numerical features Can be used for both classification and regression tasks Disadvantages: Can be sensitive to noise in the data Can overfit the data if the tree is too deep

What are the different types of hyperparameters that can be tuned in a machine learning model?

Learning rate Number of iterations Batch size Regularization parameters Activation function

What are the advantages and disadvantages of using a k-nearest neighbors algorithm for classification?

Simple to understand and implement Can handle both categorical and numerical features Can be used for both classification and regression tasks Disadvantages: Can be sensitive to noise in the data Can be computationally expensive for large datasets

What are the advantages and disadvantages of using a linear regression algorithm for regression?

Simple to understand and implement Can handle both categorical and numerical features Can be used for both classification and regression tasks Disadvantages: Can be sensitive to outliers in the data Can only model linear relationships between features and the target variable

What is the difference between supervised and unsupervised learning algorithms?

Supervised learning algorithms learn from labeled data, where the labels indicate the correct output for each input. Unsupervised learning algorithms learn from unlabeled data, where the labels are not known. types include : Classification algorithms, which predict the class label of a new data point. Regression algorithms, which predict the continuous value of a new data point.

Which of the following is NOT a disadvantage of using a linear regression algorithm for regression? a) Can be sensitive to outliers in the data b) Can only model linear relationships between features and the target variable c) Can handle both categorical and numerical features d) Easy to understand and implement

Can handle both categorical and numerical features

What is the difference between classification and regression algorithms?

Classification algorithms predict the class label of a new data point, while regression algorithms predict the continuous value of a new data point.

What are the different types of supervised learning algorithms?

Classification algorithms, which predict the class label of a new data point. Regression algorithms, which predict the continuous value of a new data point.

What are the different types of regression algorithms?

Linear regression Logistic regression Polynomial regression Decision trees Random forest

Which of the following is NOT a type of hyperparameter that can be tuned in a machine learning model? a) Learning rate b) Number of iterations c) Batch size d) Activation function e) Number of features

Number of features

What are the advantages and disadvantages of using a support vector machine for classification?

Can handle both linear and non-linear data Robust to noise in the data Can be used for both classification and regression tasks Disadvantages: Can be computationally expensive to train Difficult to interpret the results

What are the advantages and disadvantages of using a gradient boosting algorithm for classification?

Can handle both linear and non-linear data Robust to noise in the data Can be used for both classification and regression tasks Easy to interpret the results Disadvantages: Can be computationally expensive to train Can be difficult to tune the hyperparameters

Which of the following is the correct definition of a decision tree? a) A machine learning algorithm that makes predictions by recursively splitting the data into smaller subsets b) A machine learning algorithm that makes predictions by finding the best line that separates two classes of data points c) A machine learning algorithm that makes predictions by finding the best curve that separates two classes of data points d) A machine learning algorithm that makes predictions by finding the best surface that separates two classes of data points

a) A machine learning algorithm that makes predictions by recursively splitting the data into smaller subsets

Which of the following is the correct definition of a decision boundary in classification? a) The line or surface that separates different classes of data points b) The point at which the probability of belonging to one class is equal to the probability of belonging to another class c) The set of all data points that are correctly classified by a machine learning model d) The set of all data points that are incorrectly classified by a machine learning model

a) The line or surface that separates different classes of data points

Which of the following is the correct definition of a random forest? a) A machine learning algorithm that makes predictions by finding the best line that separates two classes of data points b) A machine learning algorithm that makes predictions by combining the predictions of multiple decision trees c) A machine learning algorithm that makes predictions by finding the best curve that separates two classes of data points d) A machine learning algorithm that makes predictions by finding the best surface that separates two classes of data points

b) A machine learning algorithm that makes predictions by combining the predictions of multiple decision trees

Which of the following is the correct definition of a hypothesis in machine learning? a) A function that maps input data to output predictions b) A set of assumptions about the distribution of data c) A mathematical model that describes the relationship between features and the target variable d) A measure of the performance of a machine learning model

c) A mathematical model that describes the relationship between features and the target variable