Neuro-symbolic Representation of Logic Programs Defining Infinite Sets

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 implement neural networks that can process recursive programs viewed as inductive definitions. Key words: Neurosymbolic integration, Structured learning, Mathematical theory of neurocomputing, Logic programming.

• Type: Conference
• Year: 2010
• Where: ICANN
• Authors: Ekaterina Komendantskaya, Krysia Broda, Artur S. d'Avila Garcez
• Keywords: ICANN 2010, Neural Networks, Recursive Logic Programs, Recursive Programs