Immersive visualisation of 3-dimensional spiking neural networks

Abstract

Recent development in artificial neural networks has led to an increase in performance, but also in complexity and size. This poses a significant challenge for the exploration and analysis of the spatial structure and temporal behaviour of such networks. Several projects for the 3D visualisation of neural networks exist, but they focus largely on the exploration of the spatial structure alone, and are using standard 2D screens as output and mouse and keyboard as input devices. In this article, we present NeuVis, a framework for an intuitive and immersive 3D visualisation of spiking neural networks in virtual reality, allowing for a larger variety of input and output devices. We apply NeuVis to NeuCube, a 3-dimensional spiking neural network learning framework, significantly improving the user's abilities to explore, analyse, and also debug the network. Finally, we discuss further venues of development and alternative render methods that are currently under development and will increase the visual accuracy and realism of the visualisation, as well as further extending its analysis and exploration capabilities.

VS2N : Interactive Dynamic Visualization and Analysis Tool for Spiking Neural Networks

“…For Spiking Neural Networks (SNNs), due to the asynchronous nature and spikes for communication, analyzing large networks is challenging. In [17], they present a framework for immersive and intuitive 3D visualization of the network in virtual reality, which improves the user's abilities to explore and analyze SNNs. Another work [18] presents a 3D visualization tool of SNN by visualizing individual neurons and their connections while providing interactive control over the 3D visualization.…”