Logo
User: Guest  Login
Authors:
Kissner, Michael 
Document type:
Dissertation / Thesis 
Title:
A Neural-Symbolic Framework for Mental Simulation 
Advisor:
Mayer, Helmut, Prof. Dr.-Ing. 
Referee:
Mayer, Helmut, Prof. Dr.-Ing.; Werner, Martin, Prof. Dr. rer. nat. 
Date oral examination:
30.07.2020 
Publication date:
26.10.2020 
Year:
2020 
Pages (Book):
91 
Language:
Englisch 
Keywords:
Computer Vision; Machine Learning 
Abstract:
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. The framework consists of five parts, a neural-symbolic hybrid network based on capsules for inverse graphics, an episodic memory to store observations, an interaction network for intuitive physics, a meta-learning agent that continuously improves the framework and a querying language that acts as the framework...    »
 
Department:
Fakultät für Informatik 
Institute:
INF 4 - Institut für Angewandte Informatik 
Chair:
Mayer, Helmut 
Open Access yes or no?:
Ja / Yes