Paul John Werbos (born 1947) is an American social scientist and machine learning pioneer. He is best known for his 1974 dissertation, which first described the process of training artificial neural networks through backpropagation of errors. He also was a pioneer of recurrent neural networks.
Paul J. Werbos
|Born||September 4, 1947|
|Alma mater||Harvard University|
|Awards||IEEE Neural Network Pioneer Award (1995)|
|Thesis||Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences (1974)|
|Doctoral advisor||Karl Deutsch|
|Other academic advisors||Yu-Chi Ho|
Werbos was one of the original three two-year Presidents of the International Neural Network Society (INNS). In 1995, he was awarded the IEEE Neural Network Pioneer Award for the discovery of backpropagation and other basic neural network learning frameworks such as Adaptive Dynamic Programming.
He served as program director in the National Science Foundation for several years until 2015.
- The thesis, and some supplementary information, can be found in his book, Werbos, Paul J. (1994). The Roots of Backpropagation : From Ordered Derivatives to Neural Networks and Political Forecasting. New York: John Wiley & Sons. ISBN 0-471-59897-6.
- Werbos, P. (1990). "Backpropagation Through Time: What It Does and How to Do It" (PDF). Proceedings of the IEEE. 78 (10): 1550–1560. doi:10.1109/5.58337.
- "Award Recipients | IEEE Computational Intelligence Society". cis.ieee.org. Retrieved 2017-09-12.
- Werbos, Paul J. (2005). "A Conjecture About Fermi–Bose Equivalence". arXiv:hep-th/0505023. Cite journal requires
- "Discussion with Paul Werbos on the Nature of Quantum Nonlocality". December 7, 2012.
- Home Page
- "Dr. Paul Werbos sees flex-fuels and plug-in hybrids as road to independence". Archived from the original on February 13, 2012.