Logic and probability provide two distinct frameworks for modeling how rational agents ought to draw inferences and learn from the available data in the face of uncertainty. The aim of this conference is to provide an interdisciplinary forum for bridging these two perspectives. In particular, we especially solicit submissions that combine insights and techniques from probability and logic to provide an analysis of rational learning and the conditions under which successful inductive learning can be achieved. These analyses may feature logic both in the strict sense—involving the study of formal systems and their semantics to investigate questions of expressivity, complexity, knowledge representation and inference—and in the broader sense of a systematic theory of correct reasoning and rational learning.

 

Topics of interest include, but are not limited to, logical and computability-theoretic aspects of probabilistic inference, logics for probabilistic and causal reasoning, inductive logic, statistical models of learning (including Bayesian approaches), formal learning theory, and topological approaches to learning and learnability.

Dates and Deadlines

Special Issue

The Progic Series

Contact

Acknowledgements