Skip to Main content Skip to Navigation
Conference papers

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.
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-02060063
Contributor : Hal Ifip <>
Submitted on : Thursday, March 7, 2019 - 10:37:48 AM
Last modification on : Wednesday, September 9, 2020 - 4:04:04 PM
Long-term archiving on: : Sunday, June 9, 2019 - 10:25:57 AM

File

472936_1_En_22_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

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⟩

Share

Metrics

Record views

141

Files downloads

49