Reasoning about Time and Knowledge in Neural Symbolic Learning Systems

We show that temporal logic and combinations of temporal logics and modal logics of knowledge can be effectively represented in artificial neural networks. We present a Translation Algorithm from temporal rules to neural networks, and show that the networks compute a fixed-point semantics of the rules. We also apply the translation to the muddy children puzzle, which has been used as a testbed for distributed multi-agent systems. We provide a complete solution to the puzzle with the use of simple neural networks, capable of reasoning about time and of knowledge acquisition through inductive learning.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Artur S. d'Avila Garcez, Luís C. Lamb
• Keywords: Artificial Neural Networks, Neural Networks, NIPS 2003, NIPS 2007, Temporal Logics