Please use this identifier to cite or link to this item:
Publication type: Conference paper
Type of review: Peer review (publication)
Title: Deep learning in the wild
Authors: Stadelmann, Thilo
Amirian, Mohammadreza
Arabaci, Ismail
Arnold, Marek
Duivesteijn, Gilbert François
Elezi, Ismail
Geiger, Melanie
Lörwald, Stefan
Meier, Benjamin Bruno
Rombach, Katharina
Tuggener, Lukas
DOI: 10.1007/978-3-319-99978-4_2
Proceedings: Artificial Neural Networks in Pattern Recognition
Page(s): 17
Pages to: 38
Conference details: 8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), Siena, Italy, 19-21 September 2018
Issue Date: 2018
Series: Lecture Notes in Computer Science
Series volume: 11081
Publisher / Ed. Institution: Springer
ISBN: 978-3-319-99977-7
Language: English
Subjects: Data availability; Deployment; Loss & reward shaping; Real world tasks
Subject (DDC): 006: Special computer methods
Abstract: Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.
Further description: Invited paper
Fulltext version: Accepted version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Published as part of the ZHAW project: Libra: A One-Tool Solution for MLD4 Compliance
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
ANNPR_2018d.pdfAccepted Version4.87 MBAdobe PDFThumbnail
Show full item record
Stadelmann, T., Amirian, M., Arabaci, I., Arnold, M., Duivesteijn, G. F., Elezi, I., Geiger, M., Lörwald, S., Meier, B. B., Rombach, K., & Tuggener, L. (2018). Deep learning in the wild [Conference paper]. Artificial Neural Networks in Pattern Recognition, 17–38.
Stadelmann, T. et al. (2018) ‘Deep learning in the wild’, in Artificial Neural Networks in Pattern Recognition. Springer, pp. 17–38. Available at:
T. Stadelmann et al., “Deep learning in the wild,” in Artificial Neural Networks in Pattern Recognition, 2018, pp. 17–38. doi: 10.1007/978-3-319-99978-4_2.
STADELMANN, Thilo, Mohammadreza AMIRIAN, Ismail ARABACI, Marek ARNOLD, Gilbert François DUIVESTEIJN, Ismail ELEZI, Melanie GEIGER, Stefan LÖRWALD, Benjamin Bruno MEIER, Katharina ROMBACH und Lukas TUGGENER, 2018. Deep learning in the wild. In: Artificial Neural Networks in Pattern Recognition. Conference paper. Springer. 2018. S. 17–38. ISBN 978-3-319-99977-7
Stadelmann, Thilo, Mohammadreza Amirian, Ismail Arabaci, Marek Arnold, Gilbert François Duivesteijn, Ismail Elezi, Melanie Geiger, et al. 2018. “Deep Learning in the Wild.” Conference paper. In Artificial Neural Networks in Pattern Recognition, 17–38. Springer.
Stadelmann, Thilo, et al. “Deep Learning in the Wild.” Artificial Neural Networks in Pattern Recognition, Springer, 2018, pp. 17–38,

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