automatic programming & expressivity in machine learning

from the ICML Tutorial on Automatic Inductive Programming :

The expressivity of most Machine Learning languages (attribute-value) is basically equivalent to propositional logic, excluding work on ILP. The second goal of the tutorial is to show how we can go beyond these techniques by extending the expression power of the representation language. This can be done by adding elements programmers typically use, like variables, subroutines, loops, and recursion. This way, more complex problems can be addressed.

I'm very curious about the concept of "expressivity of Machine Learning languages", so I should read these notes when I find the time.

He also has a whole section on Schmidhuber's OOPS.