Speaker: Reza Jafari, PhD
Synopsis:
In the last two decades, more attention has been given to Neural Networks and their applications. The ability of Neural Networks to solve complex problems in control, system identification, signal processing, communication, pattern recognition, etc. is well understood. Feed-forward Neural Network with feed-back connections is called Recurrent Neural Network. Recurrent Neural Networks are more powerful than feed-forward networks because of internal feed-back connections; this comes at the expense of more difficult training and the potential for instabilities. It has become more and more important to have efficient methods for determining the stability of Recurrent Neural Networks. The main contribution of this research is to develop improved methods for determining the stability of Recurrent Neural Networks.
About the Speaker:
Dr. Reza Jafari is currently the faculty member of Electrical Engineering Technology at ECPI University, Northern Virginia. He received his PhD in Electrical Engineering and second MS in Applied Mathematics both from the Oklahoma State University. He received his first MS degree in Mechatronics from the American University of Sharjah. He received his BS degree from Tehran University in 2001. He was the reviewer for different Journal papers for publication in IEEE transactions. His area of research is focused on Recurrent Neural Networks for system identification & control.
Contact the organizer for latest event info. Kodoom.com is not responsible for any changes made in the above information. Report or Flag this event
