Please use this identifier to cite or link to this item:
Publication type: Conference paper
Type of review: Peer review (abstract)
Title: Hyperparameter tuning for deep learning in natural language processing
Authors: Aghaebrahimian, Ahmad
Cieliebak, Mark
et. al: No
DOI: 10.21256/zhaw-18993
Conference details: 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 18-19 2019
Issue Date: 2019
Publisher / Ed. Institution: Swisstext
Language: English
Subject (DDC): 006: Special computer methods
Abstract: Deep Neural Networks have advanced rapidly over the past several years. However, it still seems like a black art for many people to make use of them efficiently. The reason for this complexity is that obtaining a consistent and outstanding result from a deep architecture requires optimizing many parameters known as hyperparameters. Hyperparameter tuning is an essential task in deep learning, which can make significant changes in network performance. This paper is the essence of over 3000 GPU hours on optimizing a network for a text classification task on a wide array of hyperparameters. We provide a list of hyperparameters to tune in addition to their tuning impact on the network performance. The hope is that such a listing will provide the interested researchers a mean to prioritize their efforts and to modify their deep architecture for getting the best performance with the least effort.
Fulltext version: Published version
License (according to publishing contract): Not specified
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
swisstext19_Hyperparameters.pdfHyperparameter Tuning for Deep Learning in Natural Language Processing171.02 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.