# SuperMemo Algorithm

Jump to navigation
Jump to search

**SuperMemo Algorithm** is an optimization procedure used in computing optimum intervals in spaced repetition. The algorithm has evolved since 1985 (see: Birthday of spaced repetition).

The most significant steps in the evolution of the algorithm:

- Algorithm SM-2: first computer version (1987)
- Algorithm SM-5: first fast-convergence adaptable version (1989)
- Algorithm SM-6: first version based on forgetting curves (1991)
- Algorithm SM-8: first version designed entirely on the basis of previously collected data (1995)
- Algorithm SM-17: first version based on the three component model of memory with nearly all parameters derived from dedicated data metrics (2016)
- Algorithm SM-18: based on Algorithm SM-17, uses a different model for computing item difficulty, improved approximation of the stabilization function, and several minor parameter optimizations based on the analysis of the algorithm with the universal metric (2019)

This glossary entry is used to explain "*History of spaced repetition*" by Piotr Wozniak (June 2018)