Georgi Dikov

Intuition and experience. Probably, that's the answer you would get if you happen to ask deep learning engineers how they chose the hyperparameters of a neural network. Depending on their familiarity with the problem, they might have done some good three to five full dataset runs until a satisfactory result popped up. Now, you might say, we surely could automate this, right, after all we do it implicitly in our heads? Well, yes, we definitely could, but should we?

DLRC 2018 winners!

They describe their approach

Group picture of the DLRC 2018 winners next to their Panda robot


The Deep Learning Research Challenge centres around teaching a Franka Emika Panda 7DoF Robotic Arm to classify sensor readings according to SELF, ENVIRONMENT and OTHER.

The Panda is equipped with an Intel RealSense depth camera mounted adjacent to the end effector. It captures RGB images at 480 x 640 …

Deep Variational Bayes Filter

DVBF: filter to learn what to filter

Maximilian Soelch
Learnt latent representation of a swinging pendulum

Machine-learning algorithms thrive in environments where data is abundant. In the land of scarce data, blessed are those who have simulators. The recent successes in Go or Atari games would be much harder to achieve without the ability to parallelise millions of perfect game simulations.

But in many other domains …


Machine Learning Research Lab, Volkswagen Group

Patrick van der Smagt
The front view of the lab building

Established in 2016, Volkswagen Group Machine Learning Research Lab, located in Munich, was set up as a fundamental research lab on topics close to what we think artificial intelligence is about: machine learning and probabilistic inference, efficient exploration, and optimal control.

Our research topics are championed by lab members. We …