Sparse distributed memory

Sparse distributed memory (SDM) is a mathematical model of human long-term memory introduced by Pentti Kanerva in 1988 while he was at NASA Ames Research Center.[1]

This memory exhibits behaviors, both in theory and in experiment, that resemble those previously unapproached by machines – e.g., rapid recognition of faces or odors, discovery of new connections between seemingly unrelated ideas, etc. Sparse distributed memory is used for storing and retrieving large amounts ( bits) of information without focusing on the accuracy but on similarity of information.[2] There are some recent applications in robot navigation[3] and experience-based robot manipulation.[4]

  1. ^ Cite error: The named reference book was invoked but never defined (see the help page).
  2. ^ Kanerva, Pentti (1988). Sparse Distributed Memory. The MIT Press. ISBN 978-0-262-11132-4.
  3. ^ Mendes, Mateus; Crisostomo, Manuel; Coimbra, A. Paulo (2008). "Robot navigation using a sparse distributed memory". 2008 IEEE International Conference on Robotics and Automation. pp. 53–58. doi:10.1109/ROBOT.2008.4543186. ISBN 978-1-4244-1646-2. S2CID 10977460.
  4. ^ Jockel, S.; Lindner, F.; Jianwei Zhang (2009). "Sparse distributed memory for experience-based robot manipulation". 2008 IEEE International Conference on Robotics and Biomimetics. pp. 1298–1303. doi:10.1109/ROBIO.2009.4913187. ISBN 978-1-4244-2678-2. S2CID 16650992.