Deep Learning and Morphological Computation: Friends or Foes?
AI is currently seen as equivalent to deep learning. Is that justified? Can deep learning really solve AI? That probably depends importantly on what we mean by AI. In this talk, I will argue that to produce "real" AI (whatever that is), we will have to leverage different types of computation, not just deep learning. For each of these types, of which morphological computation is another one, we have to learn how to encode appropriate priors to make computation effective, robust, and general for a particular type of problem. I will give several examples from our research to support my arguments.
Photo credit: Lip Kee Yap (CC BY-SA 2.0)
About the speaker
Oliver Brock is the Alexander-von-Humboldt Professor of Robotics in the School of Electrical Engineering and Computer Science at Technische Universität Berlin, a German "University of Excellence". He received his Ph.D. from Stanford University in 2000 and held post-doctoral positions at Rice University and Stanford University. He was an Assistant and Associate Professor in the Department of Computer Science at the University of Massachusetts Amherst before to moving back to Berlin in 2009. The research of Brock's lab, the Robotics and Biology Laboratory, focuses on robot intelligence, mobile manipulation, interactive perception, grasping, manipulation, soft material robotics, interactive machine learning, deep learning, motion generation, and the application of algorithms and concepts from robotics to computational problems in structural molecular biology. Oliver Brock directs the Research Center of Excellence "Science of Intelligence". He is an IEEE Fellow and was president of the Robotics: Science and Systems Foundation from 2012 until 2019.Registration