Visualizing Convolutional Neural Networks with Virtual Reality
| Autor: | Nadine Meissler, Annika Wohlan, Nico Hochgeschwender |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Institut für Simulations- und Softwaretechnik
Artificial neural network Computer science media_common.quotation_subject 05 social sciences Exploratory research 02 engineering and technology Virtual reality neural networks Convolutional neural network Visualization Verteilte Systeme und Komponentensoftware Presentation Human–computer interaction 0502 economics and business 0202 electrical engineering electronic engineering information engineering Rapid access virtual reality 050211 marketing 020201 artificial intelligence & image processing Software system visualization media_common knowledge learning |
| Zdroj: | VRST |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|