One key feature of TensorFlow includes the possibility to compile the trained model to run efficiently on mobile phones. This enables a wide range of opportunities for researchers and developers. In this tutorial, we teach attendees two basic steps to run neural networks on a mobile phone: Firstly, we will teach how to develop neural network architectures and train them in TensorFlow. Secondly, we show the process to run the trained models on a mobile phone.




  • Sven Mayer

    He is a Ph.D. student at the University of Stuttgart. He is part of Cluster of Excellence in Simulation Technology, in brief SimTech, funded by the German research foundation (DFG). He is generally interested in all flavors of HCI. Sven’s particular interest is in touch interaction and machine learning. His main research interest is modeling of human behavior patterns for interactive system.

  • Huy Viet Le

    He is a Ph.D. student at the University of Stuttgart, funded by the MWK Baden-Württemberg within the Juniorprofessuren-Programm and the German research foundation (DFG) within the SimTech Cluster of Excellence. His research focuses on modeling touch interaction on mobile devices. Furthermore, he is interested in extending the touch input vocabulary on mobile devices using machine learning and external sensors.

  • Niels Henze

    He is an assistant professor at the University of Stuttgart. He heads the group for socio-cognitive systems within the Institute for Visualization and Interactive Systems as well as the SimTech Cluster of Excellence in Simulation Technology. Niels is generally interested in mobile humancomputer interaction and he is particularly interested in using large-scale studies to develop models of human behavior that can improve the interaction with mobile devices.