David Everett Rumelhart (June 12, 1942 – March 13, 2011)[1] was an American psychologist who made many contributions to the formal analysis of human cognition, working primarily within the frameworks of mathematical psychology, symbolic artificial intelligence, and parallel distributed processing. He also admired formal linguistic approaches to cognition, and explored the possibility of formulating a formal grammar to capture the structure of stories.

David E. Rumelhart
Rumelhart in 1991
BornJune 12, 1942
DiedMarch 13, 2011(2011-03-13) (aged 68)
Known forConnectionism
Artificial neural network modeling
Deep Learning
Applications of backpropagation
AwardsMacArthur Fellowship (July 1987)
National Academy of Sciences
Warren Medal of the Society of Experimental Psychologists
APA Distinguished Scientific Contribution Award
University of Louisville Grawemeyer Award (2002)
Scientific career
FieldsPsychology
InstitutionsStanford University
University of California, San Diego
ThesisThe Effects of Interpresentation Intervals on Performance in a Continuous Paired-Associate Task (1967)
Doctoral advisorWilliam Kaye Estes
Doctoral studentsMichael I. Jordan
Robert J. Glushko

Early life and education

edit

Rumelhart was born in Mitchell, South Dakota on June 12, 1942. His parents were Everett Leroy and Thelma Theora (Ballard) Rumelhart.[2] He began his college education at the University of South Dakota, receiving a B.A. in psychology and mathematics in 1963. He studied mathematical psychology at Stanford University, receiving his Ph.D. in 1967.

Career

edit

From 1967 to 1987 he served on the faculty of the Department of Psychology at the University of California, San Diego. In 1987 he moved to Stanford University, serving as Professor there until 1998.

Rumelhart was elected to the National Academy of Sciences in 1991 and received many prizes, including a MacArthur Fellowship in July 1987, the Warren Medal of the Society of Experimental Psychologists, and the APA Distinguished Scientific Contribution Award. Together with James McClelland, he won the 2002 University of Louisville Grawemeyer Award in Psychology.[3]

Personal life

edit

Rumelhart became disabled by Pick's disease, a progressive neurodegenerative disease, and at the end of his life lived with his brother in Ann Arbor, Michigan. He died in Chelsea, Michigan. He is survived by two sons.[2]

Work

edit

Rumelhart was the first author of a highly cited paper from 1985[4] (co-authored by Geoffrey Hinton and Ronald J. Williams) that applied the back-propagation algorithm to multi-layer neural networks. This work showed through experiments that such networks can learn useful internal representations of data. The approach has been widely used for basic cognition researches (e.g., memory, visual recognition) and practical applications. The 1985 paper does not cite earlier publications of backpropagation, such as the 1974 dissertation of Paul Werbos,[5] as they did not know the earlier publications.[6]

Rumelhart developed backpropagation around 1982 independently.[6] In 1983, he showed it to Terry Sejnowski, who tried it and found it to train much faster than Boltzmann machines (developed in 1983).[7] Geoffrey Hinton however did not accept backpropagation, preferring Boltzmann machines, only accepting backpropagation a year later.[8]

In the same year, Rumelhart also published Parallel Distributed Processing: Explorations in the Microstructure of Cognition[9] with James McClelland, which described their creation of computer simulations of perceptrons, giving to computer scientists their first testable models of neural processing, and which is now regarded as a central text in the field of cognitive science.[1]

His 1986 work with McClelland ignited the "past tense debate" during the 1980s revival of neural networks.[10] The connectionism side debated the symbolic side, represented by Jerry Fodor, Gary Marcus, Zenon Pylyshyn, Steven Pinker, etc. The debate concerned whether neural networks or symbolic programs were adequate models for how English speakers can turn a verb into its past tense.[11][12]

Rumelhart's models of semantic cognition and specific knowledge in a diversity of learned domains using initially non-hierarchical neuron-like processing units continue to interest scientists in the fields of artificial intelligence, anthropology, information science, and decision science.

In his honor, in 2000 the Robert J. Glushko and Pamela Samuelson Foundation created the David E. Rumelhart Prize for Contributions to the Theoretical Foundations of Human Cognition.[1][13] A Review of General Psychology survey, published in 2002, ranked Rumelhart as the 88th most cited psychologist of the 20th century, tied with John Garcia, James J. Gibson, Louis Leon Thurstone, Margaret Floy Washburn, and Robert S. Woodworth.[14]

References

edit
  1. ^ a b c Carey, Benedict (March 18, 2011). "David Rumelhart Dies at 68; Created Computer Simulations of Perception". The New York Times.
  2. ^ a b "Profile details: David Everett Rumelhart". Marquis Who's Who.
  3. ^ "David E. Rumelhart: A Scientific Biography". Archived from the original on 2013-10-30. Retrieved 2016-02-03.
  4. ^ Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (1986-10-09). "Learning representations by back-propagating errors". Nature. 323 (6088): 533–536. Bibcode:1986Natur.323..533R. doi:10.1038/323533a0. ISSN 1476-4687. S2CID 205001834.
  5. ^ Werbos, Paul (November 1974). Beyond regression: New tools for prediction and analysis in the behavioral sciences (PhD). Harvard University.
  6. ^ a b Chapter 12. Rosenfeld, Edward, and James A. Anderson, eds. 2000. Talking Nets: An Oral History of Neural Networks. Reprint edition. The MIT Press.
  7. ^ Chapter 14. Rosenfeld, Edward, and James A. Anderson, eds. 2000. Talking Nets: An Oral History of Neural Networks. Reprint edition. The MIT Press.
  8. ^ Chapter 16. Rosenfeld, Edward, and James A. Anderson, eds. 2000. Talking Nets: An Oral History of Neural Networks. Reprint edition. The MIT Press.
  9. ^ David E. Rumelhart; James L. McClelland; PDP Research Group (1987). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. ISBN 9780262680530. Retrieved 2016-02-03.
  10. ^ Rumelhart, D. E.; McClelland, J. L. (1986). "On learning the past tenses of English verbs" (PDF). Parallel distributed processing: explorations in the microstructure of cognition, vol. 2: psychological and biological models. Cambridge, MA, USA: MIT Press. pp. 216–271. ISBN 978-0-262-13218-3. Retrieved 2023-11-03.
  11. ^ Seidenberg, Mark S.; Plaut, David C. (August 2014). "Quasiregularity and Its Discontents: The Legacy of the Past Tense Debate". Cognitive Science. 38 (6): 1190–1228. doi:10.1111/cogs.12147. ISSN 0364-0213. PMID 25104139. S2CID 11791286.
  12. ^ Pinker, Steven. "Four decades of rules and associations, or whatever happened to the past tense debate." Language, the brain, and cognitive development: Papers in honor of Jacques Mehler (2001): 157-179.
  13. ^ "Message 1: THE RUMELHART PRIZE Announcement and Call for Nominations". linguistlist.org.
  14. ^ Haggbloom, Steven J.; Warnick, Jason E.; Jones, Vinessa K.; Yarbrough, Gary L.; Russell, Tenea M.; Borecky, Chris M.; McGahhey, Reagan; Powell, John L. III; et al. (2002). "The 100 most eminent psychologists of the 20th century". Review of General Psychology. 6 (2): 139–152. doi:10.1037/1089-2680.6.2.139. S2CID 145668721.
edit