Intermediate Machine Learning Challenge

What is the purpose of feature scaling in machine learning?

• To increase the dimensionality of the feature space.

• To normalize the range of features to ensure equal contribution in distance-based algorithms.

• To eliminate outliers from the dataset.

• To reduce the number of features in the dataset.

Explain the difference between supervised and unsupervised learning.

• Supervised learning is only used for classification tasks.

• Supervised learning is faster than unsupervised learning.

• Supervised learning uses labeled data for training, while unsupervised learning uses unlabeled data to find patterns.

• Unsupervised learning requires more data than supervised learning.

What is overfitting, and how can it be prevented?

• Overfitting is when a model performs poorly on both training and unseen data.

• Overfitting is when a model performs well on training data but poorly on unseen data. It can be prevented by using techniques like cross-validation, regularization, and simplifying the model.

• Overfitting occurs when a model is too simple and cannot learn from the training data.

• Overfitting can be prevented by increasing the size of the training dataset only.

Describe the role of a confusion matrix in evaluating a model.

• A confusion matrix is used to visualize data distributions.

• A confusion matrix predicts future trends in data.

• A confusion matrix measures the speed of a model's predictions.

• A confusion matrix evaluates a classification model by summarizing correct and incorrect predictions.

What is cross-validation, and why is it important?

• Cross-validation is important because it helps prevent overfitting, provides a more accurate estimate of model performance, and ensures that the model generalizes well to unseen data.

• Cross-validation is a method to increase the size of the training dataset.

• Cross-validation is a technique to visualize the model's predictions.

• Cross-validation is used to reduce the complexity of the model.

Define the term 'hyperparameter' in the context of machine learning.

• Hyperparameters are the labels assigned to the training data.

• Hyperparameters are the final output of a machine learning model.

• Hyperparameters are the data used for training the model.

• Hyperparameters are configuration settings used to control the training process and model architecture in machine learning.

What is the difference between bagging and boosting?

• Bagging increases bias, while boosting increases variance.

• Bagging and boosting are the same technique with different names.

• Bagging focuses on feature selection, while boosting focuses on model complexity.

• Bagging reduces variance, while boosting reduces bias.

Explain the concept of a decision tree and its advantages.

• Advantages of decision trees include ease of interpretation, ability to handle both numerical and categorical data, minimal data preprocessing, and suitability for both classification and regression tasks.

• Decision trees require extensive data preprocessing.

• They are only suitable for numerical data.

• Decision trees cannot be used for regression tasks.

What are the assumptions of linear regression?

• Dependence of errors

• High multicollinearity

• Non-linearity

• Linearity, Independence, Homoscedasticity, Normality, No multicollinearity

How does a support vector machine (SVM) work?

• SVM minimizes the distance between all data points.

• SVM uses decision trees to classify data.

• A support vector machine (SVM) finds the optimal hyperplane that separates different classes by maximizing the margin between them.

• SVM relies on clustering techniques to group data points.