5 Classification Free Online FlashCards

What does a classification model learn to predict?

Classification learns from examples with known category labels and uses features to predict labels for new examples.

What defines binary classification?

Binary classification assigns an example to one of two possible labels.

How is logistic regression used for classification?

Logistic regression learns weighted relationships between features and classes; it can estimate class probabilities as well as predict labels.

How does a class prediction differ from a probability estimate?

A class prediction is the selected label; probability estimates express estimated likelihoods for possible labels.

How does classification differ from regression?

Classification predicts categories; regression predicts a numerical value.

What is multiclass classification?

Multiclass classification chooses among three or more mutually exclusive labels, such as apple, orange, or pear.

What distinguishes multilabel classification?

Multilabel classification allows one example to receive several labels at once, such as both beach and sunset.

How does a decision tree classify an example?

A decision tree makes a sequence of feature-based decisions to reach a class prediction; its rules can be easy to inspect.

What is the core idea of a random forest?

A random forest combines predictions from many decision trees, often improving accuracy and helping control overfitting.

What kind of boundary does an SVM seek?

An SVM seeks a class-separating boundary with a wide margin; kernels can represent more complex boundaries.

How does K-nearest neighbors make a prediction?

K-nearest neighbors predicts a label from nearby training examples, typically using a majority vote.

What simplifying assumption does Naive Bayes make?

Naive Bayes estimates class probabilities using Bayes’ theorem and assumes features are conditionally independent given the class.