Analogical reasoning is a powerful inductive mechanism, widely used in human cognition and increasingly applied in artificial intelligence. Formal frameworks for analogical inference have been developed for Boolean domains, where inference is provably sound for affine functions and approximately correct when close to affine. These results enabled the design of analogy-based classifiers. However, they do not extend to regression tasks or continuous domains.
In this series of seminars we will revisit analogical inference from a foundational perspective.
[...]
Permanent link to this information: https://m4ai.math.tecnico.ulisboa.pt/lecture_series?sgid=98
Move the mouse over the schedule to see start and end times.