CCNCS Seminar Details
Neural-Symbolic Systems for Cognitive Reasoning [Jointly with Computational Intelligence]
|Speaker:||Artur d'Avila Garcez|
|Date/Time:||Monday 13 June 2011, 2.00pm|
Although human cognition often involves the integration of reasoning and learning abilities, these are typically studied separately in computational intelligence. In our research, we seek to integrate these abilities into neural-symbolic systems, offering a unified approach to robust learning and expressive reasoning within the neural-computation paradigm. In neural-symbolic systems, a neural network offers a parallel machine for computation, inductive learning and efficient reasoning, while high-level logical representations of the machine offer rigour, modularity and explanation to the network implementation. In this talk, I review the work on neural-symbolic systems, starting from logic programming, which has already provided contributions to problems in bioinformatics and engineering. I then look at how modal logic and other forms of non-classical reasoning can be implemented in the network model. Network ensembles, each representing the knowledge of an agent at a time point, can be combined at different levels of abstraction to form modular, deep networks. These implement various reasoning tasks, including temporal, epistemic, intuitionistic, abductive, relational and uncertainty reasoning. Recently, the neural-symbolic model has been applied to the integrated verification and adaptation of software models and to online reasoning and learning in driving simulators. The results indicate that the model is capable of controlling the accumulation of errors. We claim that this simple, yet powerful model offers a basis for an expressive and computationally tractable cognitive system for integrated reasoning and robust machine learning.