论文信息 - Visualization and Exploration of Deep Learning Networks in 3D and Virtual Reality

Visualization and Exploration of Deep Learning Networks in 3D and Virtual Reality

Understanding of artificial intelligence (AI) systems becomes more important as their use cases in real-world applications growth. Today’s AI systems are increasingly complex and ubiquitous. They will be responsible for making decisions that directly affect individuals. Explainable AI can potentially help by explaining actions, decisions and behaviours of AI systems to users. Our approach is to provide a tool with an interactive user interface in 3D. The tool visualizes deep learning network layers and allows interactive exploration on different levels of detail. The visualization then improves transparency and opacity of AI systems for experts and non-experts.

Andreas Schreiber | Marcel Bock | A. Schreiber | M. Bock

[1] Arvind Satyanarayan,et al. The Building Blocks of Interpretability , 2018 .

[2] Klaus-Robert Müller,et al. Learning how to explain neural networks: PatternNet and PatternAttribution , 2017, ICLR.

[3] Andreas Schreiber,et al. Visualization of neural networks in virtual reality using Unreal Engine , 2018, VRST.

[4] Andrew Zisserman,et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[5] Geoffrey E. Hinton,et al. Visualizing Data using t-SNE , 2008 .

[6] Thomas Brox,et al. Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[7] Bolei Zhou,et al. Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8] Yoshua Bengio,et al. Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9] Minsuk Kahng,et al. ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models , 2017, IEEE Transactions on Visualization and Computer Graphics.

[10] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.