Paul Werbos
Paul J. Werbos (* 1947 ) is an American applied mathematician and pioneer of neural networks . In particular, he introduced backpropagation in his 1974 dissertation at Harvard University .
He also made other contributions to neuroinformatics, for example in recurrent neural networks .
Werbos studied at Harvard with a doctorate in applied mathematics. He also studied physics and has degrees from the London School of Economics in economics and political science.
He works as a program manager for the National Science Foundation , which he has been with since 1988. There he was temporarily responsible for electric cars and fuel cells as well as sustainable technology, later for adaptive and intelligent systems (AIS), quantum systems and their device modeling and high-voltage networks at system level. Prior to that, he developed econometric predictive models for the US Department of Energy using neural networks from 1980 to 1989 and was senior analyst for long-term energy forecasting in the US Energy Information Administration (EIA), for which he had worked since 1979. Prior to that, he was a programmer at MIT in the 1970s, taught at the University of Maryland, and worked as a mathematical statistician for a year.
He received the IEEE Neural Network Pioneer Award and was President of the International Neural Network Society (INNS), whose Hebb Award he won in 2011. He is a fellow of the IEEE .
Web links
Individual evidence
- ^ Title of the dissertation: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences
- ^ Werbos Backpropagation through time: what it does and how to do it , Proceedings of the IEEE, Volume 78, 1990, Issue 10, pp. 1550-1560
| personal data | |
|---|---|
| SURNAME | Werbos, Paul |
| ALTERNATIVE NAMES | Werbos, Paul J. |
| BRIEF DESCRIPTION | American mathematician |
| DATE OF BIRTH | 1947 |