Software systems and components are increasingly based on machine learning methods, such as Convolutional Neural Networks (CNNs). Thus, there is a growing need for common programmers and machine learning newcomers to understand the general functioning of these algorithms. However, as neural networks are complex in nature, novel presentation means are required to enable rapid access to the functionality. For that purpose, this paper examines how CNNs can be visualized in Virtual Reality. A first exploratory study has confirmed that our visualization approach is both intuitive to use and conductive to learning.
Visualizing Convolutional Neural Networks with Virtual Reality
2019 ; Sydney
2019-11-01
Conference paper
Electronic Resource
English
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images
British Library Online Contents | 2016
|Springer Verlag | 2017
|German Aerospace Center (DLR) | 2019
|