S. S. Malalur and M.T. Manry, "Feed-Forward Network Training Using Optimal Input Gains," accepted by IJCNN'09.
Category: PUBLICATION
2008
P. L. Narasimha, M.T. Manry, and F. Maldonado, "Upper Bound on Pattern Storage in Feedforward Networks," NeuroComputing, vol. 71, October 2008, pp. 3612â€" 3616.
Category: PUBLICATION
2008
P.L. Narasimha, S. Malalur, and M.T. Manry, "Small Models of Large Machines,"Proceedings of the TwentyFirst International Conference of the Florida AI Research Society, May 2008, pp.83-88.
Category: PUBLICATION
2008
P. L. Narasimha, W.H. Delashmit, M.T. Manry, Jiang Li, and F. Maldonado, "An Integrated Growing-Pruning Method for Feedforward Network Training," NeuroComputing, vol. 71, Spring 2008, pp. 2831-2847.
Category: PUBLICATION
2007
W.H. Delashmit and M.T. Manry, "A Neural Network Growing Algorithm that Ensures Monotonically Non Increasing Error", Advances in Neural Networks, vol.14, August 2007, pp.280-284.
Category: PUBLICATION
Affiliations
MEMBER
HKN
INNS
MIND
SENIOR MEMBER
IEEE
Appointments
Duration
Rank
Department / School
College / Office
University / Company
1993-PRESENT
PROFESSOR
ELECTRICAL ENGEERING
COLLEGE OF ENGINEERING
UNIVERISTY OF TEXAS AT ARLINGTON
1982-1993
ASSISTANT PROFESSOR
ELECTRICAL ENGINEERING
COLLEGE OF ENGINEERING
UNIVERISTY OF TEXAS AT ARLINGTON
1978-1982
Development Engineer
Schlumberger Well Services
1976-1978
ASSISTANT PROFESSOR
ELECTRICAL ENGINEERING
UNIVERISTY OF TEXAS AT AUSTIN
Synergistic Activities
DIRECTOR
Image Processing and Neural Networks Laboratory - Department of Electrical Engineering
EE5350 - DIGITAL SIGNAL PROCESSING (3 - 0) Time and frequency domain analyses of linear time invariant systems. Stability analyses of causal and non-causal systems using the Z-transform. FIR digital filter design. Design of frequency selective IIR digital filters using frequency transformations and the bilinear transform. Design of infinite and finite impulse response filters.
Contact Information Phone: 817-272-3483 Email: manry@uta.edu
Introduction to statistical pattern recognition. Deformation invariant and deformation variant feature extraction for class separability. Feature selection using transformation and subsetting. Decision theory and statistical learning theory. Classifier design using Bayes, nearest neighbor, and regression-based approaches. Sensor fusion. Prerequisites: EE 5350 and, EE 5302 or knowledge of probability
Contact Information Phone: 817-272-3483 Email: manry@uta.edu
Important Disclaimer: The responsibility for the accuracy of the information contained on these pages lies with the authors and user providing such information.