Seminar on Computational Learning and Adaptation


  Knowledge Acquisition using Relational Learning

Ichise Ryutaro
Center for the Study of Language and Information and Intelligent Systems Research Division, National Institute of Informatics
ichise@csli.stanford.edu

Relational learning is a widely used technique to acquire structured concepts from collections of data. Two approaches to acquire concepts represented in first order logic are inductive logic programming (ILP) and genetic programming (GP). These two approaches are very similar in terms of their methods and goals, yet their combination in previous work is rare. In this talk, we introduce an approach that synthesizes inductive logic programming and genetic programming. We also look at applications of this approach, especially to acquire knowledge in time series data.



Date: Thursday, October 11

Time: 4:15-5:30PM

Place: Cordura 100


Return to the seminar schedule