Georgia Institute of Technology
A neural network construction method for surrogate modeling of physics-based analysis
Abstract
dc:description.abstractA connectivity adjusting learning algorithm, Optimal Brain Growth (OBG) was proposed. Contrast to the conventional training methods for the Artificial Neural Network (ANN) which focus on the weight-only optimization, the OBG method trains both weights and connectivity of a network in a single training process. The standard Back-Propagation (BP) algorithm was extended to exploit the error gradient information of the latent connection whose current weight has zero value. Based on this, the OBG algorithm makes a rational decision between a further adjustment of an existing connection weight and a creation of a new connection having zero weight. The training efficiency of a growing network is maintained by freezing stabilized connections in the further optimization process. A stabilized computational unit is also decomposed into two units and a particular set of decomposition rules guarantees a seamless local re-initialization of a training trajectory. The OBG method was tested for the multiple canonical, regression and classification problems and for a surrogate modeling of the pressure distribution on transonic airfoils. The OBG method showed an improved learning capability in computationally efficient manner compared to the conventional weight-only training using connectivity-fixed Multilayer Perceptrons (MLPs).
Degree
thesis:*- Department dc:contributor.department
- Aerospace Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2012
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Sung, Woong Je
- Advisor dc:contributor.advisor
-
- Mavris, Dimitri N.
- Committee members dc:contributor.committeemember
-
- Costello, Mark
- German, Brian J.
- Kang, Sung Ha
- Volovoi, Vitali
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/43721