ABSTRACT
Many applications today use deep learning to provide intelligent behavior. To understand and explain how deep learning models come to certain decisions can be hard or completely in-transparent. We propose a visualization of convolutional neural networks in Virtual Reality (VR). The interactive application shows the internal processes and allows to inspect the results. Large networks can be visualized in real-time with special rendering techniques.
- Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dandelion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https://www.tensorflow.org/ Software available from tensorflow.org.Google Scholar
- Minsuk Kahng, Pierre Y. Andrews, Aditya Kalro, and Duen Horng (Polo) Chau. 2018. A<scp>cti</scp>V<scp>is</scp>: Visual Exploration of Industry-Scale Deep Neural Network Models. IEEE Transactions on Visualization and Computer Graphics 24, 1 (Jan 2018), 88--97.Google ScholarCross Ref
- Yann Lecun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (Nov 1998), 2278--2324.Google ScholarCross Ref
- Chris Olah, Arvind Satyanarayan, Ian Johnson, Shan Carter, Ludwig Schubert, Katherine Ye, and Alexander Mordvintsev. 2018. The building blocks of inter-pretability. Distill 3, 3 (2018), e10. https://distill.pub/2018/building-blocksGoogle ScholarCross Ref
Index Terms
Visualization of neural networks in virtual reality using Unreal Engine
Recommendations
Visualizing Convolutional Neural Networks with Virtual Reality
VRST '19: Proceedings of the 25th ACM Symposium on Virtual Reality Software and TechnologySoftware 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 ...
Neural Network Visualization in Virtual Reality: A Use Case Analysis and Implementation
Human Interface and the Management of Information: Visual and Information DesignAbstractSoftware systems and components increasingly rely on machine learning methods such as Artificial Neural Networks (ANNs) to provide intelligent functionality. Therefore, software developers and machine learning users should have a basic ...
Evaluation of Visualization Methods' Effect on Convolutional Neural Networks Research
ACAI '18: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial IntelligenceIn recent years, as an important research hotspot in the field of artificial intelligence and machine learning, the convolutional neural network has made substantial breakthroughs and has been widely used. In order to better explore and understand its ...
Comments