Verifying Properties of Neural Networks
In the beginning of nineties, Hava Siegelmann proposed a new computational model, the Artificial Recurrent Neural Network (ARNN), and proved that it could perform hypercomputation. She also established the equivalence between the ARNN and other analog systems that support hypercomputation, launching the foundations of an alternative computational theory. In this paper we contribute to this alternative theory by exploring the use of formal methods in the verification of temporal properties of ARNNs. Based on the work of Bradfield in verification of temporal properties of infinite systems, we simplify his tableau system, keeping its expressive power, and show that it is suitable to the verification of temporal properties of ARNNs.
Unable to display preview. Download preview PDF.
- 1.Bradfield, J.: Verifying Temporal Properties of Systems with Applications to Petri Nets, PhD thesis, University of Edinburgh (1991)Google Scholar
- 4.Emerson, E. A., Lei, C.-L.: Efficient Model Checking in Fragments of the Propositional Mucalculus. Proceedings of the 1st IEEE Symposium on Logic in Computer Science, (1986) 267–278Google Scholar
- 7.Neto, J. P., Siegelmann, H. T., Costa, J. F.: On the Implementation of Programming Languages with Neural Nets. In First International Conference on Computing Anticipatory Systems (CASYS’97). CHAOS, 1 (1998) 201–208Google Scholar
- 8.Neto, J. P., Siegelmann, H. T., Costa, J. F.: Building Neural Net Software. submitted, (1999)Google Scholar
- 9.Pollack, J.: On Connectionism Models of Natural Language Processing. PhD thesis. University of Illinois, Urbana (1987)Google Scholar