Image showing ways of structuring knowledge representations using directed networks.

Human learning and reasoning is founded on multiple knowledge representations with different kinds of structures, such as trees, chains, dominance hierarchies, neighborhood graphs, and directed networks. This class uses probabilistic inference methods from machine learning and Bayesian statistics, operating over different kinds of structured representational systems, to explain how people’s domain knowledge can support a wide range of learning and reasoning tasks, and how these knowledge structures may themselves be learned from experience. (Image by Prof. Joshua Tenenbaum.)