Tel. +49 (0)541 969-3353
Fax +49 (0)541 969-2246
Institute of Cognitive Science,
49090 Osnabrück, Germany
I think that a very important aspect of cognition is embodiment and believe that many of the shortcomings of current neural networks, such as vulnerability to adversarial attacks, originate from the lack of embodiment. Deep reinforcement learning is a great method to test this theory and to investigate how agents can develop an internal representation of the world with little or no rewards from the external environment.
This work is still at an early stage but here you can find some first results of my agent that I trained for the Unity Obstacle Tower Challenge.
I am especially interested in training RL agents without any rewards using mechanisms such as intrinsic curiosity. Through my background in cognitive science and neurobiology I am implementing theories about the human brain into my machine learning algorithms. I use ideas such as predictive coding and replay to move from classical machine learning techniques to more biologically motivated models.
I currently work on progressively learning and growing neural networks and combatting catastrophic forgetting once new tasks are introduced to a neural network. These solutions will then be applied to a neural network which learns to extract semantic and complex information out of images, exceeding simple pixel value descriptions or labels and trying to teach neural networks scene understanding.