A rule extraction study based on a convolutional neural network

Bologna, Guido (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland)

Convolutional Neural Networks (CNNs) lack an explanation capability in the form of propositional rules. In this work we define a simple CNN architecture having a unique convolutional layer, then a Max-Pool layer followed by a full connected layer. Rule extraction is performed after the Max-Pool layer with the use of the Discretized Interpretable Multi Layer Perceptron (DIMLP). The antecedents of the extracted rules represent responses of convolutional filters, which are difficult to understand. However, we show in a sentiment analysis problem that from these “meaningless” values it is possible to obtain rules that represent relevant words in the antecedents. The experiments illustrate several examples of rules that represent n-grams.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEPIA - Genève
Institute:
inIT - Institut d'Ingénierie Informatique et des Télécommunications
Publisher:
Hamburg, Germany, 27-30 August 2018
Date:
2018-08
Hamburg, Germany
27-30 August 2018
Pagination:
pp. 304-313
Published in:
Lecture Notes in Computer Science ; Proceedings of International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE 2018), 27-30 August 2018, Hamburg, Germany
Series Statement:
Lecture notes in computer science (LNCS), vol. 11015
DOI:
ISSN:
0302-9743
ISBN:
978-3-319-99739-1
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-08-25, last modified 2020-10-27

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)