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.

In the near future, the physicians will be able to monitor the patients at their homes using virtual reality tools, computer scientists are convinced. A team of researchers from Kaunas University of Technology (KTU), Lithuania, proposed a deep-learning-based method for the three-dimensional human shape reconstruction when the original figure is only partly visible. The main advantage of the method is its relatively low cost, high compression of the images obtained and easy integration with the existing virtual reality tools. The method was developed using a real-world dataset, the clinical trial is pending. The rapid advancements in computer vision and three-dimensional object representation enables the development of virtual reality tools and the expansion of their application sphere.