Show simple item record

dc.contributor.authorPinter, Janos D.
dc.descriptionÖzyeğin University Technical Reporten_US
dc.description.abstractAn artificial neural network (ANN) is a computational model − implemented as a computer program − that is aimed at emulating the key features and operations of biological neural networks. ANNs are extensively used to model unknown or unspecified functional relationships between the input and output of a “black box” system. In order to apply such a generic procedure to actual decision problems, a key requirement isANN training to minimize the discrepancy between modeled and measured system output. In this work, we consider ANN training as a (potentially) multi-modal optimization problem. To address this issue, we introduce a global optimization (GO) framework and corresponding GO software. The practical viability of the GO based approach is illustrated by finding close numerical approximations of (one-dimensional, but non-trivial) functions.en_US
dc.titleCalibrating artificial neural networks by global optimizationen_US
dc.typeTechnical reporten_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID(ORCID & YÖK ID 202094) Pinter, Janos
dc.contributor.ozuauthorPinter, Janos D.
dc.subject.keywordsArtificial neural networksen_US
dc.subject.keywordsANN model calibration by global optimizationen_US
dc.subject.keywordsLipschitz Global Optimizer (LGO) solver suiteen_US
dc.subject.keywordsANN implementation in Mathematicaen_US
dc.subject.keywordsMathOptimizer Professionalen_US
dc.subject.keywordsIllustrative numerical examplesen_US
dc.relation.publicationcategoryTechnical Report - Institutional Academic Staff

Files in this item


This item appears in the following Collection(s)

Show simple item record

Share this page