Flexible Reasoning of Boolean Constraints in Recurrent Neural Networks with Dual Representation
In this paper, we propose a recurrent neural network that can flexibly make inferences to satisfy given Boolean constraints. In our proposed network, each Boolean variable is represented in dual representation by a pair of neurons, which can handle four states of true, false, unknown, and contradiction. We successfully import Blake’s classical Boolean reasoning algorithm to recurrent neural network with hidden neurons of Boolean product terms. For symmetric Boolean functions, we designed an extended model of Boolean reasoning which can drastically reduce the hardware cost. Since our network has only excitatory connections, it does not suffer from oscillation and we can freely combine multiple Boolean constraints.
KeywordsBoolean constraint Boolean reasoning symmetric Boolean function recurrent neural network
Unable to display preview. Download preview PDF.
- 2.Blake, A.: Canonical expressions in Boolean algebra. University of Chicago (1938)Google Scholar
- 3.Brown, F.M.: Boolean reasoning: the logic of Boolean equations. Courier Dover Publications (2003)Google Scholar
- 4.Dietz, E.-A., Hölldobler, S., Ragni, M.: A computational logic approach to the suppression task. In: Proceedings of the 34th Annual Conference of the Cognitive Science Society, pp. 1500–1505 (2012)Google Scholar
- 8.Mandziuk, J., Macukow, B.: A neural network performing boolean logic operations. Optical Memory and Neural Networks 2(1), 17–35 (1993)Google Scholar
- 11.Spears, W.M.: A nn algorithm for boolean satisfiability problems. In: IEEE International Conference on Neural Networks, vol. 2, pp. 1121–1126. IEEE (1996)Google Scholar
- 13.Stenning, K., Van Lambalgen, M.: Human reasoning and cognitive science. The MIT Press (2008)Google Scholar
- 15.Teh, H.H.: Neural Logic Networks: A New Class of Neural Networks. World Scientific (1995)Google Scholar
- 17.Wegener, I.: The complexity of boolean functions (1987)Google Scholar