Proving properties of binary classification neural networks via Łukasiewicz logic

Logic Journal of the IGPL (forthcoming)
  Copy   BIBTEX


Neural networks are widely used in systems of artificial intelligence, but due to their black box nature, they have so far evaded formal analysis to certify that they satisfy desirable properties, mainly when they perform critical tasks. In this work, we introduce methods for the formal analysis of reachability and robustness of neural networks that are modeled as rational McNaughton functions by, first, stating such properties in the language of Łukasiewicz infinitely-valued logic and, then, using the reasoning techniques of such logical system. We also present a case study where we employ the proposed techniques in an actual neural network that we trained to predict whether it will rain tomorrow in Australia.



    Upload a copy of this work     Papers currently archived: 74,509

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Some Neural Networks Compute, Others Don't.Gualtiero Piccinini - 2008 - Neural Networks 21 (2-3):311-321.
Out of Their Minds: Legal Theory in Neural Networks. [REVIEW]Dan Hunter - 1999 - Artificial Intelligence and Law 7 (2-3):129-151.
Structural-Parametric Synthesis of Deep Learning Neural Networks.Sineglazov V. M. & Chumachenko O. I. - 2020 - Artificial Intelligence Scientific Journal 25 (4):42-51.


Added to PP

5 (#1,160,492)

6 months
5 (#144,082)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations

References found in this work

A Theorem About Infinite-Valued Sentential Logic.Robert McNaughton - 1951 - Journal of Symbolic Logic 16 (1):1-13.
Finiteness in Infinite-Valued Łukasiewicz Logic.Stefano Aguzzoli & Agata Ciabattoni - 2000 - Journal of Logic, Language and Information 9 (1):5-29.

Add more references