A Rule Extraction Study Based on a Convolutional Neural Network - Machine Learning and Knowledge Extraction Access content directly
Conference Papers Year : 2018

A Rule Extraction Study Based on a Convolutional Neural Network

Abstract

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.
Fichier principal
Vignette du fichier
472936_1_En_22_Chapter.pdf (119.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02060063 , version 1 (07-03-2019)

Licence

Attribution

Identifiers

Cite

Guido Bologna. A Rule Extraction Study Based on a Convolutional Neural Network. 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2018, Hamburg, Germany. pp.304-313, ⟨10.1007/978-3-319-99740-7_22⟩. ⟨hal-02060063⟩
100 View
109 Download

Altmetric

Share

Gmail Facebook X LinkedIn More