This talk will begin promptly at 1:30pm.
Abstract: The universal approximation capability of neural networks is exploited to recover solutions of Differential Equations. The process of solving a Differential Equation is reduced to that of training a Neural Form. Boundary conditions may be satisfied either by proper construction of the neural form, or alternatively, by treating them as constraints.
Bio: Isaac E. Lagaris
- Current Position: Professor, Department of Computer Science & Engineering, University of Ioannina
- Education: B.Sc. in Physics (1975), University of Ioannina (Ioannina, Greece)
- M.Sc. in Physics (1977) & Ph.D. in Physics (1981), University of Illinois (Champaign-Urbana, USA)
- Visiting Scientist at:
- University of Pisa, University of Lecce (Italy)
- University of South Africa, University of the Witwatersrand (S. Africa)
- COURANT Institute - New York University, Nuclear Engineering - Purdue University (USA)
- Scientific Interests:
- Local and Global optimization, Modeling & Simulation, Neural Networks, Pattern Recognition.
**This event is free and open to the public; no registration required.**