Pentti Kanerva

From Wikipedia, the free encyclopedia

Pentti Kanerva (born 1937[1]) is an American neuroscientist and the originator of the sparse distributed memory model.[2] He is responsible for relating the properties of long-term memory to mathematical properties of high-dimensional spaces and compares artificial neural-net associative memory to conventional computer random-access memory and to the neurons in the brain.[3] This theory has been applied to design and implement the random indexing approach to learning semantic relations from linguistic data.[4][5][6][7] Kanerva was also the first to use a computer clipboard to preserve deleted texts. The operation would later come to be known as cut, copy, and paste.[8]

Education and career[edit]

Kanerva has an A.A. from Warren Wilson College (1956) and an M.S. in forestry, with a minor in mathematics and statistics from the University of Helsinki, Finland (1964).[9] Kanerva worked in statistics and programming for the Finnish Forest Research Institute, the Finnish State Computer Center, and the University of Tampere, Finland, before emigrating to the United States in 1967.[9][10][11] He worked for Stanford University as a systems specialist and research assistant before earning his Ph.D. there in 1984.[9] Kanerva went on to work at NASA's Ames Research Center and the Swedish Institute of Computer Science, before taking a position at the Redwood Neuroscience Institute of the University of California, Berkeley.[10][9]

Kanerva is a member of the Cognitive Science Society, the International Neural Network Society, and the European Academy of Sciences.[9]


  1. ^
  2. ^ Kanerva, Pentti. Sparse distributed memory. MIT press, 1988.
  3. ^ "Scientific Staff". Redwood Neuroscience Institute. Archived from the original on 14 October 2002. Retrieved 11 November 2011.
  4. ^ Kanerva, Pentti, Kristoferson, Jan and Holst, Anders (2000): Random Indexing of Text Samples for Latent Semantic Analysis, Proceedings of the 22nd Annual Conference of the Cognitive Science Society, p. 1036. Mahwah, New Jersey: Erlbaum, 2000.
  5. ^ Sahlgren, Magnus, Holst, Anders and Pentti Kanerva (2008) Permutations as a Means to Encode Order in Word Space, In Proceedings of the 30th Annual Conference of the Cognitive Science Society: 1300-1305.
  6. ^ Kanerva, Pentti (2009): Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors. Cognitive Computation, Volume 1, Issue 2, pp. 139–159.
  7. ^ Joshi, Aditya, Johan Halseth, and Pentti Kanerva. "Language Recognition using Random Indexing." arXiv preprint arXiv:1412.7026 (2014).
  8. ^ Moggridge, Bill (2007). Designing interactions. Cambridge, Massachusetts: MIT Press. p. 65ff. ISBN 978-0-262-13474-3.
  9. ^ a b c d e "Pentti Kanerva". Redwood Neuroscience Institute wiki. Archived from the original on 24 November 2023. Retrieved 6 December 2023.
  10. ^ a b "Pentti Kanerva". Redwood Neuroscience Institute. Archived from the original on 22 July 2023. Retrieved 6 December 2023.
  11. ^ "Pentti Kanerva". Simons Institute. Retrieved November 24, 2023.