Next Article in Journal
Chitosan Nanocomposite Coatings for Food, Paints, and Water Treatment Applications
Next Article in Special Issue
Discriminating Emotions in the Valence Dimension from Speech Using Timbre Features
Previous Article in Journal
Autonomous Robotics for Identification and Management of Invasive Aquatic Plant Species
Previous Article in Special Issue
Disentangled Feature Learning for Noise-Invariant Speech Enhancement
Open AccessArticle

A Simple Convolutional Neural Network with Rule Extraction

Department of Computer Science, University of Applied Sciences and Arts of Western Switzerland, Rue de la Prairie 4, 1202 Geneva, Switzerland
Current address: University of Applied Sciences and Arts of Western Switzerland, Rue de la Prairie 4, 1202 Geneva, Switzerland.
Appl. Sci. 2019, 9(12), 2411; https://doi.org/10.3390/app9122411
Received: 24 April 2019 / Revised: 5 June 2019 / Accepted: 6 June 2019 / Published: 13 June 2019
(This article belongs to the Special Issue Advances in Deep Learning)
Classification responses provided by Multi Layer Perceptrons (MLPs) can be explained by means of propositional rules. So far, many rule extraction techniques have been proposed for shallow MLPs, but not for Convolutional Neural Networks (CNNs). To fill this gap, this work presents a new rule extraction method applied to a typical CNN architecture used in Sentiment Analysis (SA). We focus on the textual data on which the CNN is trained with “tweets” of movie reviews. Its architecture includes an input layer representing words by “word embeddings”, a convolutional layer, a max-pooling layer, followed by a fully connected layer. Rule extraction is performed on the fully connected layer, with the help of the Discretized Interpretable Multi Layer Perceptron (DIMLP). This transparent MLP architecture allows us to generate symbolic rules, by precisely locating axis-parallel hyperplanes. Experiments based on cross-validation emphasize that our approach is more accurate than that based on SVMs and decision trees that substitute DIMLPs. Overall, rules reach high fidelity and the discriminative n-grams represented in the antecedents explain the classifications adequately. With several test examples we illustrate the n-grams represented in the activated rules. They present the particularity to contribute to the final classification with a certain intensity. View Full-Text
Keywords: CNN; model explanation; rule extraction; sentiment analysis; n-grams CNN; model explanation; rule extraction; sentiment analysis; n-grams
Show Figures

Figure 1

MDPI and ACS Style

Bologna, G. A Simple Convolutional Neural Network with Rule Extraction. Appl. Sci. 2019, 9, 2411.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop