Isaac Lagaris: Neural Modeling and Differential Equations | IACS Seminar

Presented by Isaac Lagaris, Professor of Computer Science and Engineering, University of Ioannina Talk 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. To learn more about the IACS seminar series, please visit our website at https://iacs.seas.harvard.edu/iacs-se....