Martin Hagan
Also known as Martin T. Hagan
Martin Hagan is a professor emeritus of electrical and computer engineering at Oklahoma State University whose research applies neural networks to classification, prediction, nonlinear filtering and control. He earned a doctorate in electrical engineering at the University of Kansas in 1977, taught at the University of Tulsa from 1978, and joined Oklahoma State in 1986. In 1994 he and Mohammad Menhaj published "Training feedforward networks with the Marquardt algorithm" in IEEE Transactions on Neural Networks, and in 1996 he published the textbook Neural Network Design with Howard Demuth and Mark Beale. He won the Oklahoma State University Regents Distinguished Teaching Award in 2000. Since 2018, he is a professor emeritus, and his 2024 and 2025 papers with Joseph Kelley study multistep prediction.
Timeline
-
1972–1986
Kansas doctorate and Tulsa faculty
He earns a bachelor's degree in electrical engineering at the University of Notre Dame in 1972, a master's degree in information and computer science at the Georgia Institute of Technology in 1973, and a doctorate in electrical engineering at the University of Kansas in 1977. He works as a member of technical staff at The Analytical Sciences Corporation (TASC) in Reading, Massachusetts, from November 1977 to August 1978. In 1978, he joins the Electrical Engineering Department at the University of Tulsa as an assistant professor, and in 1984 he becomes an associate professor and graduate program coordinator there.
-
1986–1998
Associate professor at Oklahoma State
In 1986, he joins the School of Electrical and Computer Engineering at Oklahoma State University as an associate professor. In 1994, he is a visiting scholar in the University of Canterbury's Department of Electrical and Electronic Engineering in Christchurch, New Zealand, and he and Mohammad B. Menhaj publish "Training feedforward networks with the Marquardt algorithm" in IEEE Transactions on Neural Networks.
-
1996
The Neural Network Design textbook
With Howard Demuth and Mark Beale, he publishes the textbook Neural Network Design in 1996. The book presents neural network theory, design and application with MATLAB and the Neural Network Toolbox, of which he is a co-author, and it is translated into Chinese, Korean and Farsi.
-
1998–2010
Professor and control systems director
He becomes a professor in the School of Electrical and Computer Engineering at Oklahoma State University in 1998. He directs the Control Systems Engineering Program of the College of Engineering, Architecture and Technology from March 1999 to September 2010, and in 2005 and 2006 he is a visiting scholar at the Laboratoire d'Analyse et d'Architecture des Systèmes of the Centre National de la Recherche Scientifique in Toulouse, France.
-
2000–2010
Teaching awards at Oklahoma State
He wins the Oklahoma State University Regents Distinguished Teaching Award in 2000 and the Lockheed Martin Aeronautics Teaching Excellence Award in 2005 and 2010. His courses cover neural networks, stochastic processes, estimation theory, system identification and control systems.
-
2011–2014
Recurrent networks and a second edition
Neural Networks in Chemical Reaction Dynamics, which he writes with Lionel Raff, Ranga Komanduri and Satish Bukkapatnam, comes out from Oxford University Press in 2011. In 2013, his paper with Manh Cong Phan on the error surface of recurrent neural networks appears in IEEE Transactions on Neural Networks and Learning Systems. The second edition of Neural Network Design, published in 2014, adds chapters on generalization, dynamic networks, radial basis networks and practical training issues.
-
Since 2018
Professor emeritus at Oklahoma State
He becomes Professor Emeritus in the School of Electrical and Computer Engineering at Oklahoma State University in January 2018. His research uses neural networks for classification, prediction, nonlinear filtering and control.
-
2024–2025
Multistep prediction with Joseph Kelley
In 2024, he and Joseph Kelley publish a comparison of neural network NARX and NARMAX models for multi-step prediction in Expert Systems with Applications. In 2025, their paper "Adaptive Multistep Prediction With Sequence-to-Sequence (Seq2Seq) Models" appears in IEEE Transactions on Neural Networks and Learning Systems.
Career
- Since 1986Oklahoma State UniversityAssociate Professor, Professor
- 2005–2006CNRSVisiting Scholar
- 1994University of CanterburyVisiting Scholar
- 1978–1986University of TulsaAssistant Professor, Associate Professor and Graduate Program Coordinator
- 1977–1978The Analytical Sciences CorporationMember of technical staff
Education
- 1977University of KansasDoctorate in electrical engineering
- 1973Georgia Institute of TechnologyMaster's degree in information and computer science
- 1972University of Notre DameBachelor's degree in electrical engineering
Sources and credits
Photo: We have no published photo of Martin Hagan yet. Send us a free-licensed photo.



