H.B. Keller Colloquium

Can we find causal direction between two random variables without temporal precedence information? Can we figure out where latent causal variables are and how they are related, by analyzing only the measured variables? In our daily life and science, people often attempt to answer such causal questions, for the purpose of understanding, proper manipulation of systems, and robust prediction under interventions. Moreover, machine learning or artificial intelligence (AI) in complex environments has attracted much attention. For instance, how can we do transfer learning in a principled way? How can machines deal with adversarial attacks? Interestingly, it has recently been shown that causal representations may facilitate understanding and solving various AI problems. This talk focused on how to learn causal representations (with or without latent variables) from observational data and why and how the causal perspective allows adaptive prediction and a potentially higher level of artificial intelligence.