Addressing the Difficulty of Training Deep Neural Networks Using Gradient-Based Optimization Methods

Bölük, Can (2018) Addressing the Difficulty of Training Deep Neural Networks Using Gradient-Based Optimization Methods. Other thesis, TED Ankara Koleji.

[img]
Preview
Text (pdf)
Can_Boluk.pdf - Other
Available under License Creative Commons Attribution Non-commercial.

Download (908kB) | Preview

Abstract

Artificial Neural Networks (ANNs) are complex modelling techniques that can be used to find the relation between the output of a complex multivariable function and its arguments, effectively approximating it.

Item Type: Thesis (Other)
Uncontrolled Keywords: Deep Neural Networks, Artificial Neural Networks
Subjects: Q Science > QA Mathematics
Depositing User: Kamil Çömlekçi
Date Deposited: 03 Dec 2018 06:24
Last Modified: 03 Dec 2018 06:24
URI: http://tedprints.tedankara.k12.tr/id/eprint/865

Actions (login required)

View Item View Item