Professor Emeritus
School of Electrical and Computer Engineering
Oklahoma State University
Stillwater, OK 74078
(405) 744-7340
mhagan (at) okstate.edu
| Courses | Brief Biography | Professional |
| Academic Background | Selected Publications | Areas of Interest |
|
New Edition of Neural Network Design
Textbook (with Python Demos) |
||
Top
Ph.D., Electrical Engineering, University of Kansas, 1977.
M.S., Information and Computer Science, Georgia Institute of Technology,
1973.
B.S., Electrical Engineering, University of Notre Dame, 1972.
Machine Learning, Neural Networks, Deep Learning, System Identification, Time Series Analysis, Control Systems, Signal Processing
Dr. Hagan has taught and conducted research in the areas of machine learning, statistical modeling and control systems for the last forty years. His research has encompassed a variety of application areas: drug discovery, molecular dynamics, seismic signal processing, genetic pathway modeling, optimal portfolio management, electric load prediction, flight simulators, precision pointing systems, diesel engines, adaptive flight control and friction compensation. He has received grants from Boeing, Texas Instruments, Halliburton Energy Services, Cummins Engine Company, National Science Foundation, Air Force Office of Scientific Research, California Public Employees Retirement System (CalPERS), Amgen, and FlightSafety International. For the last thirty years his research has focused on the use of neural networks for classification, prediction, nonlinear filtering and control. He is author, with Howard Demuth and Mark Beale, of a textbook, Neural Network Design, which has been translated into Chinese, Korean and Farsi. He is also a co-author of the Neural Network Toolbox for MATLAB. He has given keynote addresses on neural networks at a variety of international conferences. He was a visiting scholar during 1994 at the University of Canterbury in Christchurch, New Zealand and during 2005-2006 at the Laboratoire d'Analyse et d'Architecture des Systèms du Centre National de la Recherche Scientifique in Toulouse, France. He has taught courses in neural networks, stochastic processes, estimation theory, system identification and control systems. He was awarded the Oklahoma State University Regents Distinguished Teaching Award in 2000 and the Lockheed Martin Aeronautics Teaching Excellence Award in 2005 and 2010.
J. Kelley and M. Hagan. "Comparison of neural network NARX and NARMAX models for multi-step prediction using simulated and experimental data." Expert Systems with Applications, vol. 237 (2024): 121437.
M. Taye, D. Morrow, J. Cull, D.H. Smith, and M. Hagan, "Deep Learning for FAST Quality Assessment," Journal of Ultrasound in Medicine, vol. 42, no. 1, pp. 71-79, 2023.
J. Kelley and M. Hagan, "New Fault Diagnosis Procedure and Demonstration on Hydraulic Servo-Motor for Single Faults," IEEE/ASME Transactions on Mechatronics, vol. 25, no. 3, pp. 1499-1509, June 2020.
A. Jafari and M. Hagan, “Application of new training methods for neural model reference control,” Engineering Applications of Artificial Intelligence, Volume 74, September 2018, Pages 312-321.
D. Hagan and M. Hagan. "Soft Computing Tools for Virtual Drug Discovery."
Journal of Artificial Intelligence and Soft Computing Research, Vol. 8,
No. 3 (2018): 173-189.
N. Nourshamsi, M. Hagan, and C. Bunting. "Estimation of required absorbing
material dimensions inside metal cavities using neural networks." In
Electromagnetic Compatibility & Signal/Power Integrity (EMCSI), 2017
IEEE International Symposium on, pp. 69-74. IEEE, 2017.
D. Hagan and M. Hagan, “Virtual Drug Screening Using Neural Networks,”
Proceedings of the International Joint Conference on Neural Networks
(IJCNN), Vancouver, CA, July, 2016.
M. Alam, P. Patil, M. Hagan, D. Chandler, “A computational model for predicting local distortion visibility via convolutional neural network trained on natural scenes,” IEEE International Conference on Image Processing (ICIP), 2015, pp. 3967 - 3971.
A. Jafari, and M. Hagan. "Enhanced recurrent network training," Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1-8., July, 2015.
R. Jafari, A. Kable and M. Hagan, “Forward and Converse Lyapunov Theorems for Discrete Dynamical Systems,” IEEE Transactions on Automatic Control, Vol. 59, No. 9, pp. 2496 - 2501, September, 2014.
M. Phan and M. Hagan, “Error Surface of Recurrent Networks,” IEEE Transactions on Neural Networks and Learning Systems, Vol. 24, No. 11, pp. 1709 - 1721, October, 2013.
M. Phan and M. Hagan, "A Procedure for Training Recurrent Networks," International Joint Conference on Neural Networks, August 2013, Dallas, TX, Paper No. 1420.
L. M. Raff, R. Komanduri, M. T. Hagan, and S. T. Bukkapatnam, Neural Networks in Chemical Reaction Dynamics, Oxford University Press, 2011.
A. Pukrittayakamee, M. Hagan, L. Raff, S. Bukkapatnam, R. Komanduri, “Practical training framework for fitting functions and their derivatives,” IEEE Transactions on Neural Networks, Vol. 22, No. 6, pp. 936 - 947, June 2011.
M. Malshe, L. M. Raff, M. Hagan, S. Bukkapatnam, and R. Komanduri, “Input vector optimization of feed-forward neural networks for fitting ab initio potential-energy databases,” The Journal of Chemical Physics, 132, 204103, 2010.
M. Malshe, A. Pukrittayakamee, L. M. Raff, M. Hagan, S. Bukkapatnam, and R. Komanduri, “Accurate prediction of higher-level electronic structure energies for large databases using neural networks, Hartree-Fock energies, and small subsets of the database,” The Journal of Chemical Physics, 131, 124127, 2009.
M. Malshe, R. Narulkar, L. Raff, M. Hagan, S. Bukkapatnam, P. Agrawal, and R. Komanduri, “Development of generalized potential-energy surfaces (GPES) using many-body expansions, neural networks (NN), and moiety energy (ME) approximations,” The Journal of Chemical Physics, 130, 184102, 2009.
A. Pukrittayakamee, M. Malshe, M. Hagan, L. M. Raff, R. Narulkar, S. Bukkapatnum and R. Komanduri, “Simultaneous fitting of a potential-energy surface and its corresponding force fields using feedforward neural networks,” The Journal of Chemical Physics, 130, 134101, 2009.
J. Horn, O. De Jesús and M. Hagan, “Spurious Valleys in the Error Surface of Recurrent Networks - Analysis and Avoidance,” IEEE Transactions on Neural Networks, Vol. 20, No. 4, pp. 686-700, April 2009.
P.M. Agrawal, M. Malshe , R. Narulkar , L.M. Raff, M. Hagan, S. Bukkapatnum and R. Komanduri , “A Self-Starting Method for Obtaining Analytic Potential-Energy Surfaces from ab Initio Electronic Structure Calculations,” The Journal of Physical Chemistry, A, Vol. 113, No. 5, pp. 869-877, Feb., 2009.
M. Malshe, R. Narulkar, L. M. Raff, M. Hagan, S. Bukkapatnam and R. Komanduri, “Parametrization of analytic interatomic potential functions using neural networks,” The Journal of Chemical Physics, 129, 044111, 2008.
L. Hamm, B. W. Brorsen and M. T. Hagan, "Comparison of Stochastic Global Optimization Methods to Estimate Neural Network Weights," Neural Processing Letters, Vol. 26, No. 3, December 2007.
O. De Jesus and M. Hagan, "Backpropagation Algorithms for a Broad Class of Dynamic Networks," IEEE Transactions on Neural Networks, Vol. 18, No. 1, January 2007, pp. 14 -27.
P.M. Agrawal, L.M. Raff, M. Hagan, and R. Komanduri, "Molecular dynamics investigations of the dissociation of SiO{_2} on ab initio potential energy surface obtained using neural network methods," The Journal of Chemical Physics, 124, 134306 (2006).
Agrawal, P.M., A.N.A. Samadh, L.M. Raff, M. Hagan, S. T. Bukkapatnam, and R. Komanduri, "Prediction of molecular-dynamics simulation results using feedforward neural networks: Reaction of a C2 dimer with an activated diamond (100) surface," The Journal of Chemical Physics, 123, 224711 (2005).
Raff, L.M., M. Malshe, M. Hagan, D.I. Doughan, M.G. Rockley, and R. Komanduri, "Ab initio potential-energy surfaces for complex, multi-channel systems using modified novelty sampling and feedforward neural networks," The Journal of Chemical Physics, 122, 084104 (2005).
M. Hagan, H. Demuth, O. De Jesus, "An Introduction to the Use of Neural Networks in Control Systems," International Journal of Robust and Nonlinear Control, Vol. 12, No. 11, September, 2002, pp. 959-985. Related Software Demos
Torii, M. and M. Hagan , "Stability of Steepest Descent with Momentum for Quadratic Functions," IEEE Transactions on Neural Networks, Vol. 13, No. 3, May 2002, pp. 752 -756.
F. Farbiz, M. Menhaj, S. Motamedi, and M. Hagan, "A New Fuzzy Logic Filter for Image Enhancement," IEEE Transactions on Systems, Man and Cybernetics, Vol. 30, No. 1, February 2000.
M. Hagan, O. De Jesus, and R. Schultz, "Training Recurrent Networks for Filtering and Control," Chapter 11 of Recurrent Neural Networks:Design and Applications, L.R. Medsker and L.C. Jain, Eds., CRC Press, 1999, pp. 325-354.
M. Fun and M. Hagan, "Recursive Orhogonal Least Squares Learning with Automatic Weight Selection for Gaussian Neural Networks," International Joint Conference on Neural Networks, July 1999, Washington, Paper No. 322.
R. Schultz and M. Hagan, "Training Multiloop Networks," International Joint Conference on Neural Networks, July 1999, Washington, Paper No. 514.
R. Schultz and M. Hagan, "On-Line Least Squares Learning for the Underdetermined Case," International Joint Conference on Neural Networks, July 1999, Washington, Paper No. 515.
D. Chen and M. Hagan, "Optimal Use of Regularization and Cross-Validation in Neural Network Modeling," International Joint Conference on Neural Networks, July 1999, Washington, Paper No. 323.
M. Hagan and H. Demuth, "Neural Networks for Control," Invited Tutorial, 1999 American Control Conference, June, 1999, San Diego, pp. 1642-1656.
C. James, M. Hagan, R. Jones, P. Bones, and G. Carrol, "Neural Network Based Spatio-Temporal Filtering of the EEG via Multireference Adaptive Noise Canceling," IEEE Transactions on Biomedical Engineering. Vol. 44, No. 8, pp. 775-780, 1997.
D. Foresee and M. Hagan, "Gauss-Newton Approximation to Bayesian Learning," Proceedings of the 1997 International Joint Conference on Neural Networks.
M. Fun and M. Hagan, "Levenberg-Marquardt Training for Modular Networks, " Proceedings of the 1996 International Conference on Neural Networks, pp. 468-473, 1996.
M. Hagan, H. Demuth, and M. Beale, Neural Network Design, Boston, MA: PWS Publishing, 1996.
M. Hagan and C. Latino, "A Modular Control Systems Laboratory, " Computer Applications in Engineering Education Vol. 3, No. 2, 1995, pp. 89-96.
M. Hagan and M. Menhaj, "Training Feedforward Networks with the Marquardt Algorithm, " IEEE Transactions on Neural Networks, Vol. 5, No. 6, November 1994, pp. 989-993.
Y. Zhang and M. Hagan, "A Reduced Parameter Bilinear Time Series Model, " IEEE Transactions on Signal Processing, Vol. 42, No. 7, July 1994, pp. 1867-1870.
M. Menhaj and M. Hagan, "Analysis of Delays in Networked Flight Simulators, " IEEE Transactions on Systems, Man and Cybernetics, Vol. 24, No. 6, June 1994, pp. 875-881.
M. Hagan, N. Sammur, G. Guimaraes, C. Latino and J. Hamalainen, "Distributed Control Loading and Motion for Flight Simulation," Progress in Simulation, Vol. 2, Ablex Publishing, 1994, pp. 52-90.
N. Sammur and M. Hagan, "Mapping Signal Processing Algorithms on Parallel Architectures," Journal of Parallel and Distributed Computing, Vol. 8, No. 2, February 1990.
M. Hagan and S. Behr, "The Time Series Approach to Short Term Load
Forecasting," IEEE Transactions on Power Apparatus and Systems,
Vol. PWRS-2, No. 3, pp. 785-791, August 1987.
Top