Dangerous Deep Learning: How The Machines Can Hit The Wall

23 Pages Posted: 16 Jun 2020

See all articles by Frank Lehrbass

Frank Lehrbass

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting); FOM University of Applied Sciences for Economics and Management; University of the Bundesbank

Date Written: May 22, 2020


Democratization of the mysterious art of data science via Amazon Web Services, Google Cloud Platform, Microsoft Azure, and other machine learning (ML) service providers might make it too easy to apply ML. To underline this we present a worked-out example in R (including sources in the appendix), where deep learning falls behind much simpler methods or learns something that is not there. We start with 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 to the inputs. The reason for this is highlighted by visual data analysis. Then we exemplify how a multi-layer perceptron (MLP) is lured into learning a function y=f(x), where there is no relation between y and x. Summing up, we demonstrate how a mighty CNN learns less than a two-feature based logistic regression and how a simple MLP learns more than a linear regression when there is nothing to learn! One way to avoid these pitfalls is academic training in data science.

Keywords: Image Recognition, CNN, MLP, Spurious Regression, Microsoft Azure

JEL Classification: C01, C02, C19, C55

Suggested Citation

Lehrbass, Frank and Lehrbass, Frank, Dangerous Deep Learning: How The Machines Can Hit The Wall (May 22, 2020). Available at SSRN: https://ssrn.com/abstract=3607952 or http://dx.doi.org/10.2139/ssrn.3607952

Frank Lehrbass (Contact Author)

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


HOME PAGE: http://lehrbass.de

FOM University of Applied Sciences for Economics and Management ( email )

Toulouser Allee 53
Dusseldorf, 40476

University of the Bundesbank ( email )

Hachenburg, 57627

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics