Lachine Mearning. Borotics. Irtificial Antelligence.
I'm currently working as an Applied Scientist at Amazon Core Machine Learning Berlin.
Before starting my position at Amazon, I was a research assistant/PhD student at the Robotics & Biology Lab, TU Berlin. During my PhD, I have been working on a wide variety of topics in the area of artificial intelligence, ranging from robotics, computer vision and artificial language evolution to reinforcement, unsupervised and semi-supervised learning. Before my time in academia, I co-founded and worked for several internet start-ups in Berlin.
28/06/2017: PhD thesis successfully defended!
28/02/2017: My spotlight talk on Unsupervised Learning of State Representations for Multiple Tasks presented at the NIPS Workshop on Deep Learning for Action and Interaction is now available online on youtube.
A small collection of projects that I did during the last years.
Research paper on learning state representations in multi-task reinforcement learning.
The paper has been presented at the NIPS Workshop on Deep Learning for Action and Interaction. The spotlight talk is online on youtube.
Lightweight ML framework for learning with side information (aka privileged information), based on Theano and Lasagne.
Accompanies our paper Patterns for Learning with Side Information which I presented at the Berlin Machine Learning Group Meetup at Amazon ML. (slides)
Research paper on coupled learning of relational forward models and action parameters, presented at IROS 2016.
My blog on teaching machine learning and artificial intelligence without formal math.
In May 2015, our Team RBO won a prestigious international robotics challenge.
The lessons learned paper won the Best Systems Paper award at RSS 2016; the paper on the perception system got nominated for Best Paper Award at IROS 2016.
In 2007, I was working for younginternet, developing an online gaming platform for children.
