Deep Nothing: How to Hit the Wall With Deep Learning

14 Pages Posted: 2 Jan 2019

See all articles by Frank Lehrbass

Frank Lehrbass

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting)

Date Written: December 17, 2018

Abstract

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.

Keywords: Deep Learning, Image Recognition, CNN, MLP, MXNet

JEL Classification: C01, C02, C19, C55

Suggested Citation

Lehrbass, Frank, Deep Nothing: How to Hit the Wall With Deep Learning (December 17, 2018). Available at SSRN: https://ssrn.com/abstract=3302491 or http://dx.doi.org/10.2139/ssrn.3302491

Frank Lehrbass (Contact Author)

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting) ( email )

Dusseldorf
Germany

HOME PAGE: http://lehrbass.de

Register to save articles to
your library

Register

Paper statistics

Downloads
47
Abstract Views
382
PlumX Metrics