loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock
Exact and Approximate Rule Extraction from Neural Networks with Boolean Features

Topics: Applications: Image Processing and Artificial Vision, Pattern Recognition, Decision Making, Industrial and Real World Applications, Financial Applications, Neural Prostheses and Medical Applications, Neural Based Data Mining and Complex Information Process; Learning Paradigms and Algorithms

Authors: Fawaz A. Mereani 1 and Jacob M. Howe 2

Affiliations: 1 City, University of London, London, U.K., Umm AL-Qura University, Makkah and Saudi Arabia ; 2 City, University of London, London and U.K.

Keyword(s): Neural Networks, XSS, Rule Extraction, Explainable AI.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Biomedical Engineering ; Biomedical Signal Processing ; Computational Intelligence ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Learning Paradigms and Algorithms ; Methodologies and Methods ; Neural Networks ; Neurocomputing ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Sensor Networks ; Signal Processing ; Soft Computing ; Theory and Methods

Abstract: Rule extraction from classifiers treated as black boxes is an important topic in explainable artificial intelligence (XAI). It is concerned with finding rules that describe classifiers and that are understandable to humans, having the form of (I f...Then...Else). Neural network classifiers are one type of classifier where it is difficult to know how the inputs map to the decision. This paper presents a technique to extract rules from a neural network where the feature space is Boolean, without looking at the inner structure of the network. For such a network with a small feature space, a Boolean function describing it can be directly calculated, whilst for a network with a larger feature space, a sampling method is described to produce rule-based approximations to the behaviour of the network with varying granularity, leading to XAI. The technique is experimentally assessed on a dataset of cross-site scripting (XSS) attacks, and proves to give very high accuracy and precision, compar able to that given by the neural network being approximated. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.142.196.0

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Mereani, F. and Howe, J. (2019). Exact and Approximate Rule Extraction from Neural Networks with Boolean Features. In Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - NCTA; ISBN 978-989-758-384-1; ISSN 2184-3236, SciTePress, pages 424-433. DOI: 10.5220/0008362904240433

@conference{ncta19,
author={Fawaz A. Mereani and Jacob M. Howe},
title={Exact and Approximate Rule Extraction from Neural Networks with Boolean Features},
booktitle={Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - NCTA},
year={2019},
pages={424-433},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008362904240433},
isbn={978-989-758-384-1},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - NCTA
TI - Exact and Approximate Rule Extraction from Neural Networks with Boolean Features
SN - 978-989-758-384-1
IS - 2184-3236
AU - Mereani, F.
AU - Howe, J.
PY - 2019
SP - 424
EP - 433
DO - 10.5220/0008362904240433
PB - SciTePress