IMLQ1

Which of the following is not true for machine learning?

• Supervised learning uses labeled data and aims to predict outcomes.

• Unsupervised learning uses unlabeled data and aims to uncover hidden patterns or structures.

• Clustering, for example, grouping customers into segments based on purchasing behavior) is an example of supervised learning.

• Classification, for example, identifying whether an email is spam or not is an example of supervised learning.

What is a common application of unsupervised learning?

• Image classification where each image is labeled with a category.

• Market basket analysis to find associations between products purchased together.

• Sentiment analysis to determine the sentiment of a given text.

• Spam detection where emails are classified as spam or not.

Which of the following best describes overfitting in machine learning?

• When a model is too simple to capture the underlying patterns in the data.

• When a model generalizes well to new data.

• When a model performs well on training data but poorly on unseen data.

• When a model is trained on too little data.

Given that feature selection is the process of selecting a subset of the original features based on their importance and relevance, and Feature Extraction is Combining or transforming the original features into a new set of features that represent the most important information. Which one is true?

• Feature extraction algorithm looks at the original features and evaluates their relevance to the task. The most important features are kept, and less important features are removed.

• Feature selection aims to reduce dimensionality by creating new features that summarize or combine the original data in a way that makes the model more efficient while retaining the essential information.

• A technique that combines the features into a set of new, uncorrelated features called principal components would be an example of Feature extraction.

• Feature extraction aims to reduce the dimensionality of the dataset by selecting the most important features, improving the model's performance and interpretability, and reducing overfitting.

What is a primary goal of clustering in unsupervised learning?

• To reduce the dimensionality of the dataset.

• To predict future outcomes based on labeled data.

• To group similar data points together based on their features.

• To classify data into predefined categories.

In the context of feature engineering, what is the purpose of normalization?

• To increase the number of features in the dataset.

• To scale the features to a similar range to improve model performance.

• To remove irrelevant features from the dataset.

• To create new features based on existing ones.

Which of the below descriptions suggest the learning will not be impacted by scaling thhe features?

• A model making predictions based on the conditional probability of the features.

• A model which considers the relative ordering of feature values rather than their absolute magnitudes.

• A model which uses Euclidean distance to assign data points to clusters.

• A model which works by calculating the distance between data points (usually Euclidean distance).