DeepAI AI Chat
Log In Sign Up

Neural Networks as Artificial Specifications

by   I. S. W. B. Prasetya, et al.
Utrecht University

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.


page 1

page 2

page 3

page 4


A Rice's Theorem for Abstract Semantics

Classical results in computability theory, notably Rice's theorem, focus...

Verifying Programs via Intermediate Interpretation

We explore an approach to verification of programs via program transform...

GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts

Program synthesis is the task to automatically generate programs based o...

Probabilistic Neural Programs

We present probabilistic neural programs, a framework for program induct...

Self-Replicating Neural Programs

In this work, a neural network is trained to replicate the code that tra...

Lessons learned from replicating a study on information-retrieval based test case prioritization

Objective: In this study, we aim to replicate an artefact-based study on...