The first Human-aligned AI Summer School will be held in Prague from 2nd to 5th August. The focus of the first year will be on “learning from humans,” including subtopics such as inverse reinforcement learning, modeling bounded rational agents and latest trends in AI alignment research.
The school is focused on teaching approaches and frameworks, less on presentation of latest research results. The content of the school is mostly technical - it is assumed the attendees understand current ML approaches such as deep learning. The intended audience of the school are researchers interested in learning more about the AI alignment topics, PhDs, researchers working in ML/AI outside academia, and talented students.
Daniel Braun is Professor of Learning Systems at Ulm University. He habilitated in neural and behavioral biology and cognitive science at the Eberhard Karls Universität Tübingen. Previously, he was a visiting PhD student and postdoctoral research associate in the Computational and Biological Learning Laboratory Cambridge University and a visiting scientist in the Computational Learning and Motor Control Laboratory at the University of Southern California. In 2011 he was awarded an Emmy-Noether-fellowship by the Deutsche Forschungsgemeinschaft to establish the independent research group “Sensorimotor Learning and Decision-making” at the Max-Planck-Institutes for Biological Cybernetics and Intelligent Systems in Tübingen. In 2015 he was awarded an ERC Starting Grant “BRISC: Bounded rationality in sensorimotor coordination”. He has doctorates in natural science and philosophy from the Albert-Ludwigs-Universität, Freiburg, in the subject areas of computational neuroscience and philosophy of mind respectively.
His research interests include cognitive modelling, decision-making and bounded rationality,a abstraction and structural learning, sensorimotor learning and control, learning robots and biological information processing
Viktoriya Krakovna is a research scientist in AI safety at DeepMind, and co-founder of the Future of Life Institute. Her PhD thesis in statistics and machine learning at Harvard University focused on building interpretable models. Viktoriya gained numerous distinctions for her accomplishments in math competitions, including a silver medal at the International Mathematical Olympiad and the Elizabeth Lowell Putnam prize.
Daniel Filan is currently pursuing his PhD at CHAI, University of California under Stuart Russell, working on mathematics relevant to the AI alignment problem. His latest publications include Modeling Agents with Probabilistic Programs (together with Owain Evans, Andreas Stuhlmuller, and John Salvatier) and Self-Modification of Policy and Utility Function in Rational Agents (together with Tom Everitt, Mayank Daswani, and Marcus Hutter). Previously he studied he theory of reinforcement learning, mathematics, and theoretical physics at the Australian National University. In a program similar to research masters degree, he wrote a thesis on "Resource-bounded Complexity-based Priors for Agents", under Marcus Hutter.
Katja Grace is a researcher at the Machine Intelligence Research Institute. Her interests include AI forecasting, game theory, and anthropic reasoning.
Miles Brundage is Research Fellow at FHI and a PhD candidate in Human and Social Dimensions of Science and Technology at Arizona State University. He is also affiliated with the Consortium for Science, Policy, and Outcomes (CSPO), the Virtual Institute of Responsible Innovation (VIRI), and the Journal of Responsible Innovation (JRI). His recent research focuses on the societal implications of artificial intelligence.
Prior to starting graduate school, he worked at the Advanced Research Projects Agency - Energy (ARPA-E) for two years, and interned for the Institute for Human and Machine Cognition (IHMC).