no code implementations • 5 Aug 2020 • Michael Kissner
We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation.
4 code implementations • 18 Nov 2019 • Michael Kissner
A large chunk of research on the security issues of neural networks is focused on adversarial attacks.
1 code implementation • 23 May 2019 • Michael Kissner, Helmut Mayer
Many current methods to learn intuitive physics are based on interaction networks and similar approaches.
1 code implementation • 22 May 2019 • Michael Kissner, Helmut Mayer
We follow the idea of formulating vision as inverse graphics and propose a new type of element for this task, a neural-symbolic capsule.