Neural Networks as Artificial Specifications

I. S. W. B. Prasetya, Minh An Tran

Research output: Working paperPreprintAcademic

Abstract

In theory, a neural network can be trained to act as an artificial specification for a program by showing it samples of the programs executions. In practice, the training turns out to be very hard. Programs often operate on discrete domains for which patterns are difficult to discern. Earlier experiments reported too much false positives. This paper revisits an experiment by Vanmali et al. by investigating several aspects that were uninvestigated in the original work: the impact of using different learning modes, aggressiveness levels, and abstraction functions. The results are quite promising.
Original languageEnglish
PublisherarXiv
DOIs
Publication statusPublished - 15 Sept 2018

Keywords

  • cs.SE

Fingerprint

Dive into the research topics of 'Neural Networks as Artificial Specifications'. Together they form a unique fingerprint.

Cite this