Neural-symbolic cognitive agents: architecture, theory and application

In real-world applications, the effective integration of learning and reasoning in a cognitive agent model is a difficult task. However, such integration may lead to a better understanding, use and construction of more realistic multiagent models. Existing models are either oversimplified or require too much processing time, which is unsuitable for online learning and reasoning. In particular, higher-order concepts and cognitive abilities have many unknown temporal relations with the data, making it impossible to represent such relationships by hand. In this paper, we develop and apply a Neural-Symbolic Cognitive Agent (NSCA) model for online learning and reasoning that seeks to effectively represent, learn and reason in complex real-world applications.