Learning theory and programs to date are inductively bounded: they can be described as "wind-up toys" which can only learn the kinds of things that their designers envisi...
This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial...
We have previously shown how the discovery of classes from objects can be automated, and how the resulting class organization can be e ciently optimized in the case where the opti...
While existing learning techniques can be viewed as inducing programs from examples, most research has focused on rather narrow classes of programs, e.g., decision trees or logic ...
It has been one of the great challenges of neuro-symbolic integration to represent recursive logic programs using neural networks of finite size. In this paper, we propose to imple...
Ekaterina Komendantskaya, Krysia Broda, Artur S. d...