UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Generalization Error in Deep Learning

Jakubovitz, D; Giryes, R; Rodrigues, MRD; (2019) Generalization Error in Deep Learning. In: Boche, H and Caire, G and Calderbank, R and Kutyniok, G and Mathar, R and Petersen, P, (eds.) Compressed Sensing and Its Applications. (pp. pp. 153-193). Birkhäuser Boston: Berlin, Germany. Green open access

[thumbnail of 1808.01174.pdf]
1808.01174.pdf - Accepted Version

Download (540kB) | Preview


Deep learning models have lately shown great performance in various fields such as computer vision, speech recognition, speech translation, and natural language processing. However, alongside their state-of-the-art performance, it is still generally unclear what is the source of their generalization ability. Thus, an important question is what makes deep neural networks able to generalize well from the training set to new data. In this chapter, we provide an overview of the existing theory and bounds for the characterization of the generalization error of deep neural networks, combining both classical and more recent theoretical and empirical results.

Type: Proceedings paper
Title: Generalization Error in Deep Learning
Event: Third International MATHEON Conference 2017
Location: Tech Univ Berlin, Berlin, GERMANY
Dates: 04 December 2017 - 08 December 2017
ISBN-13: 978-3-319-73073-8
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-319-73074-5_5
Publisher version: https://doi.org/10.1007/978-3-319-73074-5_5
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10086807
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item