A Virtual Reality Tool for Representing, Visualizing and Updating Deep Learning Models
This addresses the problem of limited transparency in deep learning for end users in novel application areas, though it is incremental as it builds on existing visualization and interaction techniques.
The authors tackled the lack of transparency in deep learning by developing a virtual reality tool that visualizes datasets as point clouds, allowing users to categorize data through gestures, which triggers movements mapped to machine learning concepts like latent space and backpropagation. The result is a tangible interface that aims to make neural networks more interpretable and accelerate autonomous development by end users.
Deep learning is ubiquitous, but its lack of transparency limits its impact on several potential application areas. We demonstrate a virtual reality tool for automating the process of assigning data inputs to different categories. A dataset is represented as a cloud of points in virtual space. The user explores the cloud through movement and uses hand gestures to categorise portions of the cloud. This triggers gradual movements in the cloud: points of the same category are attracted to each other, different groups are pushed apart, while points are globally distributed in a way that utilises the entire space. The space, time, and forces observed in virtual reality can be mapped to well-defined machine learning concepts, namely the latent space, the training epochs and the backpropagation. Our tool illustrates how the inner workings of deep neural networks can be made tangible and transparent. We expect this approach to accelerate the autonomous development of deep learning applications by end users in novel areas.