The goal of inductive machine learning is to take some training data and use it to induce (that is, generalize from specific data) a function f . The resulting function f will be evaluated on the test data. The machine learning algorithm has succeeded if its performance on the test data is high -- this is typically measured by looking at the difference between values returned by the function f and a known correct value.

Learning problems

• Regression: trying to predict a real value. For instance, predict the value of a stock tomorrow given its past performance. Or predict your score on the a final exam based on your homework scores.
• Binary Classification: trying to predict a simple yes/no response. For instance, predict whether a given person will enjoy a movie or not. Or predict whether a user review of the newest Apple product is positive or negative about the product.
• Multiclass Classification: trying to put an example into one of a number of classes. For instance, predict whether a news story is about entertainment, sports, politics, religion, etc., or predict whether a CS course is Systems, Theory, AI or Other.
• Ranking: trying to put a set of objects in order of relevance. For instance, predicting what order to put web pages in, in response to a user query. Or predict a person's ranked preferences over movies they have not watched.

References:

• CIML: Hal Daume III, A Course in Machine Learning 0.9, 2014 (Online).