You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at http://www.ieee.org/web/publications/rights/copyrightpolicy.html)
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at http://www.acm.org/pubs/copyright_policy/)
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact webmaster@ide.mdh.se

Abstraction-based Reduction of Input Size for Neural Networks

Authors:

Peter Backeman, Edin Jelačić, Cristina Seceleanu, Ning Xiong, Tiberiu Seceleanu

Research group:

Formal Modelling and Analysis of Embedded Systems

Publication Type:

Conference/Workshop Paper

Venue:

Bridging the Gap Between AI and Reality: First International Conference, AISoLA 2023

Abstract

Machine learning is an increasingly popular method for modeling complex system. A common machine learning model is the neural network. They can be trained to represent complicated functions to a high accuracy. However they often grow large and complex. Recent work is looking in how to abstract networks to yield simpler representation, while retaining some property of the original network, e.g., for every input the abstracted networks output is at least as large as the original. In this work, we build on previous ideas and extend it to also consider the input layer. Sometimes, the input vector has a large size, while only a few of the elements are significant in the computation of the output. In this paper, we propose to use a trained neural network model to identify insignificant input elements, i.e, elements which do not contain important information. We show how the presented abstraction method for the input layer can be utilized to achieve this.

Bibtex

@inproceedings{Backeman7371,
author = {Peter Backeman and Edin Jelačić and Cristina Seceleanu and Ning Xiong and Tiberiu Seceleanu},
title = {Abstraction-based Reduction of Input Size for Neural Networks},
editor = {Tiziana Margaria},
booktitle = {Bridging the Gap Between AI and Reality: First International Conference, AISoLA 2023},
url = {http://www.es.mdu.se/publications/7371-}
}