Supervised Learning Concepts Quiz

A machine learning type where a model learns to predict from labeled examples, each paired with a prediction value.

A value associated with an observation in supervised learning, representing what is being predicted.

A supervised learning problem where the output has only two possible values (0 or 1).

A machine learning type where the algorithm learns from labeled data, associating inputs with desired outputs.

Machine learning where the algorithm learns from unlabeled data to find patterns and structures without explicit guidance.

Learning method that uses both labeled and unlabeled data to train a model.

Machine learning where an agent learns to make decisions in an environment to maximize rewards.

A method that aims to minimize the error on the training data.

Predicting a categorical output from an input, dividing into classes.

Classifying data into more than two groups.

Data used to evaluate a machine learning model's performance on unseen data.

Data used to tune hyperparameters or select the best model.

A technique to evaluate model performance using different subsets of the data for training and testing.

The balance to strike between a model fitting too closely to training data (high variance) and being too simple to capture necessary patterns (high bias).

A machine learning algorithm that classifies data points based on the majority class of their k-nearest neighbors in the training dataset.

A method for classifying data points by finding the closest data point in the training set and assigning the same class.

A tessellation of the plane that divides the plane into regions that are closer to one point compared to others.

An approach to machine learning where the model does not learn a general representation of the data during training, instead it delays the learning until a prediction is needed.

A flowchart-like model that uses a tree-like structure to make decisions based on the features of a dataset.

Classification and Regression Trees, a method for growing decision trees.

Combining multiple models to improve accuracy and robustness.

A parallel ensemble method that builds multiple models from different subsets of the training dataset to reduce variance.

Predicting complex output values like vectors, images, graphs, or sequences.

Learning from unlabeled data by modeling observations to understand them.

Grouping similar data points in datasets.

Another word for Clustering, dividing data into groups.

A model's ability to make accurate predictions on new, unseen data.

When a model learns the training data too well, including noise, leading to poor generalization on new data.

Errors or inaccuracies in data used for training, due to measurement errors or human mistakes.

Errors arising from the process of measuring data, often due to instruments/sensors limitations.

Errors in classifying or categorizing data, frequently caused by human errors.

The set of all possible functions that a supervised learning model can choose from to map input data to output predictions.

A type of machine learning where a model learns to predict an output value from labeled input data.

A function that measures how well a model's predictions match the actual output values.

The best-performing function within the hypothesis space, as judged by the cost function.

A learning strategy where an optimal model is selected such that its predictions are as accurate as possible on the training examples.

A set of labeled observations, used to train a model.

The actual function used to map inputs to outputs in the training data.

Selecting the appropriate set of potential functions for the model to search through for the best fit.