4 Machine Learning Basics Free Online FlashCards

What is the goal of machine learning?

Machine learning builds software that learns patterns from data to make predictions or decisions; the goal is to perform well on new examples, not just memorize training data.

What kind of outcome does regression predict?

Regression predicts a numerical value, such as an apartment’s sale price.

What data does supervised learning use?

Supervised learning learns from labeled examples and is used for tasks such as classification and regression.

What are the roles of training, validation, and test data?

Training data fits model parameters, validation data supports development choices, and test data is held back for final evaluation.

What is overfitting?

Overfitting occurs when a model performs strongly on training examples but more weakly on new data, often because it has memorized training examples.

How does cross-validation compare models when data is limited?

Cross-validation repeatedly trains on all but one part of development data and validates on the held-out part, rotating which part is held out. The final model is then evaluated on the untouched test set.

How do a model and an algorithm differ?

A model is the learned function; an algorithm is the learning procedure that adjusts the model.

What are features and labels?

Features are the inputs in a data example; in supervised learning, a label is the desired answer.

What kind of outcome does classification predict?

Classification predicts a category, such as whether an email is spam or not spam.

What distinguishes unsupervised learning?

Unsupervised learning finds structure in data without supplied answer labels; clustering is one example.

What data does semi-supervised learning combine?

Semi-supervised learning combines a smaller labeled set with a larger unlabeled set, which can help when labeling is costly.

How does reinforcement learning guide an agent’s choices?

In reinforcement learning, an agent takes actions in an environment and learns from rewards or penalties to improve its choices.