A Connectionist Cognitive Model for Temporal Synchronisation and Learning

Abstract

The importance of the efforts towards integrating the sym-bolic and connectionist paradigms of artificial intelligence has been widely recognised. Integration may lead to more effective and richer cognitive computational models, and to a better understanding of the processes of artificial intelligence across the field. This paper presents a new model for the representation, computation, and learning of temporal logic in connectionist systems. The model allows for the encod-ing of past and future temporal logic operators in neural net-works, through a neural-symbolic translation algorithms in-troduced in the paper. The networks are relatively simple and can be used for reasoning about time and for learning by examples with the use of standard neural learning algo-rithms. We validate the model in a well-known application dealing with temporal synchronisation in distributed knowl-edge systems. This opens several interesting research paths in cognitive modelling, with potential applications in agent technology, learning and reasoning.