Calibrating artificial neural networks by global optimization

Name: Calibrating artificial neural networks by global optimization
Author: Pinter, Janos D.

İsim	Calibrating artificial neural networks by global optimization
Yazar	Pinter, Janos D.
Basım Tarihi:	2010-07
Konu	Artificial neural networks, ANN model calibration by global optimization, Lipschitz Global Optimizer (LGO) solver suite, ANN implementation in Mathematica, MathOptimizer Professional, Illustrative numerical examples
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Kayıt Numarası	ac59c9f9-2747-46aa-a7df-77f130a3e813
Lokasyon	Industrial Engineering
Tarih	2010-07
Notlar	Özyeğin University Technical Report
Örnek Metin	An 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.

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Calibrating artificial neural networks by global optimization

Yazar Pinter, Janos D.

Basım Tarihi 2010-07

Konu Artificial neural networks, ANN model calibration by global optimization, Lipschitz Global Optimizer (LGO) solver suite, ANN implementation in Mathematica, MathOptimizer Professional, Illustrative numerical examples

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Kayıt Numarası ac59c9f9-2747-46aa-a7df-77f130a3e813

Lokasyon Industrial Engineering

Tarih 2010-07

Notlar Özyeğin University Technical Report

Örnek Metin An 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.