Amirkabir University of Technology

About: Amirkabir University of Technology is a education organization based out in Tehran, Iran. It is known for research contribution in the topics: Nonlinear system & Finite element method. The organization has 15254 authors who have published 31165 publications receiving 487551 citations. The organization is also known as: Tehran Polytechnic & Tehran Polytechnic University.

A systematic review on overfitting control in shallow and deep neural networks

Abstract: Shallow neural networks process the features directly, while deep networks extract features automatically along with the training. Both models suffer from overfitting or poor generalization in many cases. Deep networks include more hyper-parameters than shallow ones that increase the overfitting probability. This paper states a systematic review of the overfit controlling methods and categorizes them into passive, active, and semi-active subsets. A passive method designs a neural network before training, while an active method adapts a neural network along with the training process. A semi-active method redesigns a neural network when the training performance is poor. This review includes the theoretical and experimental backgrounds of these methods, their strengths and weaknesses, and the emerging techniques for overfitting detection. The adaptation of model complexity to the data complexity is another point in this review. The relation between overfitting control, regularization, network compression, and network simplification is also stated. The paper ends with some concluding lessons from the literature.

Identification of a time-dependent coefficient in a partial differential equation subject to an extra measurement

Abstract: The problem of recovering a time-dependent coefficient in a parabolic partial differential equation has attracted considerable recent attention. Several finite difference schemes are presented for identifying the function u(x, t) and the unknown coefficient a(t) in a one-dimensional partial differential equation. These schemes are developed to determine the unknown properties in a region by measuring only data on the boundary. Our goal has been focused on coefficients that presents physical quantities, for example, the conductivity of a medium. For the convenience of discussion, we will present the results of numerical experiment on several test problems. © 2004 Wiley Periodicals, Inc. Numer Methods Partial Differential Eq, 2005