Critical Challenges for the Visual Representation of Deep Neural Networks

Date

2018

Authors

Browne, Kieran
Swift, Ben
Gardner, Henry

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Abstract

Artificial neural networks have proved successful in a broad range of applications over the last decade. However, there remain significant concerns about their interpretability. Visual representation is one way researchers are attempting to make sense of these models and their behaviour. The representation of neural networks raises questions which cross disciplinary boundaries. This chapter draws on a growing collection of interdisciplinary scholarship regarding neural networks. We present six case studies in the visual representation of neural networks and examine the particular representational challenges posed by these algorithms. Finally we summarise the ideas raised in the case studies as a set of takeaways for researchers engaging in this area.

Description

Keywords

Citation

Source

Type

Book chapter

Book Title

Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent

Entity type

Access Statement

License Rights

DOI

10.1007/978-3-319-90403-0_7

Restricted until

2099-12-31