spin glass models

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but may have typos and misspellings.

Spin glass models are used in physics to explain how magnetic materials that initially have spins (generating their magnetic moment) in random directions, settle down to have spins aligned over patches or the entire material. They are used as an analogy for subsymbolic machine learning including Boltzmann machines and Hopfield networks.

Used in Chap. 6: page 80

Used in glossary entries: Boltzmann machine, hopfield networks, machine learning