competitive learning

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

Competitive learning refers to forms of unsupervised learning where nodes compete in a winner-takes-all fashion for inputs. Kohonen networks are a classic example and k-means can be seen as a simple form of competative learning. Competitive learning is used in compression algorithms using vector quantization, which can be thought of as a little like k-means with very large k.