How does machine learning relate to artificial intelligence?

For example, is it a subset?

Are they two separate fields in Computer Science?

I have hear conflicting information: one professor said they are synonyms. However, in the courses taught at Stanford CS they are two distinct classes:

CS221 (Artificial Intelligence)

and

CS229 (Machine Learning)

Machine Learning is a subset of (the scientific field of) Artificial Intelligence.

What is ML?

Machine Learning is defined by Tom Mitchel:


A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.

Hence: When you write an algorithm that gets better the more data you give it, then you can call it ML.

What is AI but not ML?

• SLAM

• Path finding: Bellman–Ford algorithm, A* search algorithm, Dijkstra's algorithm

• Markov chains

• cellular automata

• Logic: Although a lot of people (e.g. Pedro Domingos) include logic approaches (e.g. with inverse deduction) in Machine Learning, I would rather say it is AI.

• Fuzzy logic (see Fuzzy logic vs AI vs Machine learning vs Deep learning)

• Knowledge representation / Formal systems

See also

• Difference between machine learning and artificial intelligence

StackExchange Computer Science Q#86816, answer score: 6