• Media type: E-Book
  • Title: Deep Nothing : How to Hit the Wall With Deep Learning
  • Contributor: Lehrbass, Frank [Author]
  • Published: [S.l.]: SSRN, [2019]
  • Extent: 1 Online-Ressource (14 p)
  • Language: English
  • DOI: 10.2139/ssrn.3302491
  • Identifier:
  • Origination:
  • Footnote: Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments December 17, 2018 erstellt
  • Description: We present a worked out example in R (including sources in the appendix), where deep learning falls behind much simpler methods. It is an already published application of a LeNet style convolutional neural network (CNN) for image recognition. We show that this complex CNN is outperformed by a single layer perceptron and that a logistic regression comes close if done naively and also outperforms if a transformation is applied on the inputs. The reason for this is highlighted by visual data analysis
  • Access State: Open Access