We are pleased to invite you to our first meet-up on Artificial Intelligence taking place on November 23rd. In this talk, Prof. Dr. Patrick van der Smagt will talk about machine learning and biological movement behaviour.
• Doors open at 18:00; food will be provided
• Talk starts at 19:00
• Drinks as of 20:00
Deep learning is increasingly successful in task domains that, until recently, were human: image classification, face recognition, gaming, audio transcription, ... but we're far from recreating a human brain. Arguing that similarities are only phenomenological, we'll discuss how that still helps in improving machine intelligence. Examples will focus on movement representation and robotics.
In his talk he will show how we can understand and replicate biological movement behaviour, and use those to obtain efficient approximations to optimal control in complex agents.
Patrick will demonstrate how probabilistic inference can be used to obtain efficient neural networks. He will then extend this method for time series modelling.
Patrick van der Smagt is head of the Volkswagen Group AI Research Lab in Munich’s Data Lab, focussing on deep learning for robotics. He previously directed a joint lab on biomimetic robotics and machine learning as professor for computer science at TUM and head of the ML lab at fortiss Munich.
Besides publishing numerous papers and patents on machine learning, robotics, and motor control, he has won various awards, including the 2013 Helmholtz-Association Erwin Schrödinger Award, the 2014 King-Sun Fu Memorial Award, and the 2013 Harvard Medical School/MGH Martin Research Prize.
He is founding chairman of a non-for-profit organisation for Assistive Robotics for tetraplegics and co-founder of various companies.
A basic understanding of Neural Networks is strongly recommended. For a Neural Network primer see links below.